Below every paper are TOP 100 most-occuring words in that paper and their color is based on LDA topic model with k = 7.
(It looks like 0 = reinforcement learning, 1 = deep learning, 2 = structured learning?, 3 = optimization?, 4 = graphical models, 5 = theory, 6 = neuroscience)
Toggle LDA topics to sort by:
TOPIC0
TOPIC1
TOPIC2
TOPIC3
TOPIC4
TOPIC5
TOPIC6
Learning Stochastic Feedforward Neural Networks
Yichuan Tang, Ruslan Salakhutdinov
Yichuan Tang, Ruslan Salakhutdinov
[deterministic, algorithm, belief, total, state] [hidden, learning, output, test, trained, training, learn, face, dataset, sigmoid, table, weight, boltzmann, average, feedforward, input, large, image, learned, better, generative, second, performance, mlp] [binary, inference, multimodal, synthetic, network, generate] [stochastic, number, gradient, random, small, true, standard, proposed] [model, sfnns, distribution, conditional, sfnn, mixture, gaussian, log, sampling, modeling, conditioned, prior, facial, generated, posterior, figure, data, expression, exact, restricted, variational, selected, monte, carlo, residual, foreground, estimate, toronto, proposal, gibbs, hybrid] [density, note, structured, database, function, approximation, linear, set] [neural, noise]
Auditing: Active Learning with Outcome-Dependent Query Costs
Sivan Sabato, Anand D. Sarwate, Nati Srebro
Sivan Sabato, Anand D. Sarwate, Nati Srebro
[algorithm, bound, upper, return, best, setting, optimal, greedy, assume, conference, strategy, logarithmic, golovin, total] [learning, negative, class, unlabeled, large, labeled, learn, hidden, approach, international, work, achieve] [size, binary, factor] [error, number, true, random, reduction] [sample, dependence, distribution, positive, probability, respect, draw, journal, data] [active, auditing, complexity, label, hypothesis, cost, pool, query, set, realizable, agnostic, consider, point, passive, lower, general, theorem, version, machine, labeling, case, denote, lemma, result, dimension, function, approximation, minimizing, procedure, provide, easy, minimal, question, hold, depend, rectangle, consistent, access, select] [simple, threshold, corresponding]
A message-passing algorithm for multi-agent trajectory planning
Jose Bento, Nate Derbinsky, Javier Alonso-Mora, Jonathan S. Yedidia
Jose Bento, Nate Derbinsky, Javier Alonso-Mora, Jonathan S. Yedidia
[planning, algorithm, initial, agent, absolute, total, unconstrained, space, goal] [performance, multiple, international, based, approach, work] [local, global, associated, update, outgoing, variable, allows, graph, search, incoming, move] [optimization, method, convergence, admm, solve, number, supplementary, minimum, objective, solving, magnitude, standard, order, computing] [time, figure, wall, joint, describe, journal] [set, cost, problem, energy, solution, radius, function, bipartite, paper, min, consensus, maximum, formulation] [minimizer, velocity, trajectory, twa, minimizers, collision, coll, corresponding, static, robotics, logic, position, avoid, material, motion, kinetic, avoidance, receives, certainty, gcoll, account]
Inferring neural population dynamics from multiple partial recordings of the same neural circuit
Srini Turaga, Lars Buesing, Adam M. Packer, Henry Dalgleish, Noah Pettit, Michael Hausser, Jakob Macke
Srini Turaga, Lars Buesing, Adam M. Packer, Henry Dalgleish, Noah Pettit, Michael Hausser, Jakob Macke
[partial, bound, upper] [predict, approach, well, prediction, large, second, accuracy, predicted, predicting, dataset, better, performance, multiple, demonstrate, applied] [real, size, underlying] [method, true, matrix, number, random] [model, observed, data, naive, latent, estimate, computational, figure, joint, gaussian, time] [linear, subset, statistical, lower] [population, activity, imaging, neural, calcium, noise, stitching, coupling, neuron, imaged, recorded, connectivity, simultaneously, dynamical, system, stimulus, estimated, session, correlation, fully, inferring, simulated, mouse, awake, anesthetized, experimental, somatosensory, correlated, circuit, recording, infer, neuronal, whisker, cortex, unobserved, overlap, functional, correspond, presented, spiking]
Multi-Prediction Deep Boltzmann Machines
Ian Goodfellow, Mehdi Mirza, Aaron Courville, Yoshua Bengio
Ian Goodfellow, Mehdi Mirza, Aaron Courville, Yoshua Bengio
[best] [training, dbm, learning, trained, well, hinton, good, deep, mlp, net, hidden, salakhutdinov, layerwise, train, layer, dbms, boltzmann, negative, input, approach, predict, feature, better, generative, mnist, test, prediction, unit, weight, rbm, norb, centering, based, work, outperforms, performance, average, trick, ability, maximize] [inference, missing, probabilistic, perform, graphical] [standard, order, objective, number, solving, optimization, error, solve, stochastic, rate, performs, phase] [model, variational, log, sampling, markov, figure, centered, joint, observed, three, distribution, likelihood] [procedure, machine, set, point, approximation, simply, case, example, note, lower] [recurrent, single]
Adaptive Submodular Maximization in Bandit Setting
Victor Gabillon, Branislav Kveton, Zheng Wen, Brian Eriksson, S. Muthukrishnan
Victor Gabillon, Branislav Kveton, Zheng Wen, Brian Eriksson, S. Muthukrishnan
[expected, policy, item, adaptive, step, regret, gain, state, bound, greedy, algorithm, upper, choosing, choose, chosen, return, assumption, cumulative, episode, setting, assume, genre, bandit, optimistic, oasm, rated, arm, movie, highest, interacting, maximizing, elicitation, restrictive] [learning, based, learn, approach, learned, work, vector, second, context, applied, propose] [computed, sensor, associated] [number, analysis, method] [model, probability, distribution, selected, figure, major, observation, three, observed] [submodular, problem, maximization, function, max, machine, set, prove, studied, loss, main, dom, lemma, result, theorem, denote] [preference, user, study, earlier, viewed]
Approximate Inference in Continuous Determinantal Processes
Raja Hafiz Affandi, Emily Fox, Ben Taskar
Raja Hafiz Affandi, Emily Fox, Ben Taskar
[algorithm, space, sampled, provided] [based, similarity, quality, propose, approach, large, directly, accuracy, learning] [compute, synthetic, computed, real] [method, phase, matrix, dual, fourier, random, distance, eigendecomposition, number, error, wide, analysis, rate, spanned] [kernel, dpp, sampling, continuous, mixture, sample, dpps, discrete, repulsive, gibbs, iid, data, rff, probability, model, sampler, gaussian, entropy, posterior, modeling, conditional, diverse, full, approximate, three, distribution, inverse, selected, iris, estimate, considered, cdf, estimation, repulsion] [density, function, point, approximation, set, consider, case, complexity, note, machine, lower, approximating] [determinantal, range, activity, location, human, spatial]
Multiclass Total Variation Clustering
Xavier Bresson, Thomas Laurent, David Uminsky, James von Brecht
Xavier Bresson, Thomas Laurent, David Uminsky, James von Brecht
[total, algorithm, previous, simplex, conference, sum, initial, fact, step] [mtv, well, international, class, unsupervised, report, learning, image, vector] [clustering, vertex, graph, splitting, recursive, weighted, partition] [variation, convex, spectral, nmf, denotes, matrix, projection, cheeger, minimize, random, number, cut, requires, operator, exactly, optimization, grant] [data, discrete, continuous, model, figure, processing, form, university, equal] [set, function, energy, proximal, solution, indicator, relaxation, multiclass, transductive, problem, theorem, proxt, smooth, version, framework, rely, lsd, machine, note, denote, minimization, nmfr, tight, easily, subset, formation, manner, case, procedure] [sharp, simple, corresponding, constraint, exponent]
Reservoir Boosting : Between Online and Offline Ensemble Learning
Leonidas Lefakis, François Fleuret
Leonidas Lefakis, François Fleuret
[learner, online, algorithm, greedy, computationally, strategy, choosing, optimal, inria, conference, chosen, assumption, solely, best, maximizing, step] [weak, reservoir, boosting, learning, vector, geem, training, dataset, approach, propose, table, weight, based, work, practice, entire, common, computer, boosted, large, outperforms, performance, well, mnist] [weighted, size, ensemble] [number, iteration, method, matrix, proposed, covariance, row, order, optimization, comparison, column] [sample, sampling, process, computational, three, data, inverse, full, gaussian, expectation, address, model] [set, cost, subset, consider, budget, access, complexity, note, framework, case, main, dimension, loss, batch, discard] [presented, calculation, simple, refers]
Matrix factorization with binary components
Martin Slawski, Matthias Hein, Pavlo Lutsik
Martin Slawski, Matthias Hein, Pavlo Lutsik
[algorithm, step, linearly] [approach, achieved, second, box, performance] [binary, dna, compute, factor, candidate, contained, underlying, ground] [matrix, factorization, number, methylation, findvertices, uniqueness, reduction, solving, block, additional, small, order, alpha, random, analysis, nmf, hottopixx, scheme, quad, solve, coordinate, separable, row, singular, rank, checked] [data, figure, exact, independent, probability, mixture, model, drawn, approximate, parameter, discrete, computational, positive, indicates, bernoulli, referred, continuous, yielding] [problem, linear, case, set, theorem, solution, consider, result, dimension, condition, imposed, complexity, note, lemma, proposition, theory] [noise, corresponding, cell, constraint, single]
Learning to Pass Expectation Propagation Messages
Nicolas Heess, Daniel Tarlow, John Winn
Nicolas Heess, Daniel Tarlow, John Winn
[choice, goal] [learned, training, learning, approach, work, learn, challenging, sigmoid, target, evaluate, output, large, second, performance, context, experiment, forward, trained] [factor, message, inference, product, network, compound, probabilistic, incoming, compute, variable, implemented, propagation, passing, outgoing, xout, generate, person, graphical, directed, computation, allows, implement] [number, random, standard, true, rate, fast, computing] [model, distribution, gamma, sampling, data, approximate, gaussian, mixture, bayesian, posterior, figure, gaussians, expectation, drawn, sampler, drawing, accurate, generated, prior, family, marginal] [function, set, approximation, analytic, general, regression, framework, note, ball, formulation, program, cost] [neural, shape]
Latent Structured Active Learning
Wenjie Luo, Alex Schwing, Raquel Urtasun
Wenjie Luo, Alex Schwing, Raquel Urtasun
[algorithm, space, setting, step, exp, uncertainty, expected, employ, initial, advantage] [learning, prediction, labeled, training, unlabeled, test, context, supervised, image, performance, approach, large, task, output, amount, good, based, learn, composed, well, input, segmentation, feature] [variable, local, graph, inference, graphical, separate, computation, reduce, perform, extra] [random, number, error, proposed, convex, required, requires, order, convergence, iteration] [latent, joint, data, entropy, model, distribution, marginal, probability, time, selected, full, figure, likelihood] [active, structured, label, labeling, set, function, note, layout, problem, queriespixelwise, weakly, query, example, batch, interested, general, cost, paper, case, consider, select] [fully, single]
Two-Target Algorithms for Infinite-Armed Bandits with Bernoulli Rewards
Thomas Bonald, Alexandre Proutiere
Thomas Bonald, Alexandre Proutiere
[arm, algorithm, regret, horizon, optimal, explore, lim, bandit, failure, policy, achieves, reward, exploration, exploit, bound, explored, anytime, best, exploited, expected, assume, fact, berry, played, current, total, previous, setting, sequence] [target, large, average, second, propose, based, consists, performance] [larger, beta, distributed] [number, unknown, random, rate, analysis, proposed, uniformly, stochastic, phase] [time, distribution, parameter, bernoulli, selected, probability, prior, length, considered, sampling] [lower, support, proposition, theorem, case, version, proof, consider, note, set, problem, equivalent, conjecture, prove, provide, statistical, inequality, close, asymptotically, general, function, denote] [uniform, depends, corresponding, respective, false, arbitrarily]
RNADE: The real-valued neural autoregressive density-estimator
Benigno Uria, Iain Murray, Hugo Larochelle
Benigno Uria, Iain Murray, Hugo Larochelle
[natural, previous, conference, chosen] [rnade, mog, training, hidden, autoregressive, learning, test, pixel, better, performance, image, zoran, work, output, scale, dataset, trained, table, nade, large, measured, boltzmann, timit, datasets, international, validation, speech, input, logl, predicted] [network, factor, size, graphical, represent, probabilistic, product] [number, standard, gradient, small, order] [mixture, model, data, conditional, distribution, gaussians, gaussian, likelihood, conditionals, modeling, parameter, figure, probability, processing, journal, discrete, restricted, minibatch, drawn, measuring, hyperparameters, component, sample] [density, machine, set, laplace, statistical, linear] [neural, range, sharing]
Multiscale Dictionary Learning for Estimating Conditional Distributions
Francesca Petralia, Joshua T. Vogelstein, David Dunson
Francesca Petralia, Joshua T. Vogelstein, David Dunson
[algorithm, assume, strategy, choose, space] [approach, scale, performance, learning, dictionary, applied, compare, accuracy, bottom, large, feature] [tree, variable, partition, graph, scaling] [cpu, subspace, decomposition, faster, number, random, dimensional, fast, error, standard] [conditional, data, multiscale, bayesian, msb, distribution, time, predictive, figure, estimation, computational, posterior, sample, journal, partitioning, nonlinear, estimate, ambient, model, cart, latent, mixture, including, probability, swissroll, manifold, simulation, prior, family, indicates, gaussian, three, nonparametric, measure] [density, linear, statistical, set, regression, function, example, union, dimension, lasso, estimating, note, selection, creativity, squared] [neuroscience, described, automated, fully]
Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
Po-Ling Loh, Martin J. Wainwright
Po-Ling Loh, Martin J. Wainwright
[assumption, bound, observe, assume] [vector, applied, level, work, applies, predicted, class] [local, global, rsc, size] [error, gradient, optimization, descent, convex, regularized, write, require, objective, convergence, minimum] [log, plot, parameter, figure, form, sample, restricted, estimation, additive, probability, model] [statistical, linear, nonconvex, function, loss, regression, composite, theorem, theory, logistic, arg, corrected, min, optimum, program, scad, suppose, regularizers, penalty, case, corollary, opt, mcp, empirical, guaranteed, errstat, annals, consider, condition, establish, feasible, provide, convexity, main, loh, depict, lasso, constant, penalized, theoretical, hold, solution, problem, point, general] [population, strong, corresponding]
Rapid Distance-Based Outlier Detection via Sampling
Mahito Sugiyama, Karsten Borgwardt
Mahito Sugiyama, Karsten Borgwardt
[conference, best, assume, bound, algorithm, chosen, space, maximized] [detection, object, large, datasets, average, knowledge, score, qkthsp, international, table, performance, approach, better, discovery, qkthnn, introduced, outperforms, based, effectiveness, learning, inliers, randomly] [size, acm, implemented, local, cluster, sigkdd, computation, mining, scalability, neighbor] [outlier, number, method, qsp, small, outlierness, proposed, distance, analysis, popular, comparison, iterative, random, performs] [sample, sampling, data, time, probability, gaussian, parameter, computational, process, log, including, detect, respect] [set, complexity, theoretical, note, theorem, function, maximum, statistical, subset] [experimental, simple]
Better Approximation and Faster Algorithm Using the Proximal Average
Yao-Liang Yu
Yao-Liang Yu
[algorithm, assumption, sum, choice] [average, better, based, work, complicated] [group, improvement, graph] [convex, gradient, method, convergence, fast, analysis, proposed, norm, accelerated, objective, rate, siam, key, optimization, faster, alternating, solving, iterative, scheme] [component, figure, continuous, smoothing, approximate, journal] [proximal, map, approximation, nonsmooth, smooth, function, proposition, subgradient, fused, case, apg, lipschitz, example, point, simply, lasso, strictly, composite, moreau, easily, general, note, constant, consider, envelop, set, minimization, theoretical, iff, structured, clearly, clear, problem, denote, technical, machine, complexity, ultimate, statistical, fij, main, smoothness, linear] [simple, overlapping, recall, property, uniform, desired]
Dynamic Clustering via Asymptotics of the Dependent Dirichlet Process Mixture
Trevor Campbell, Miao Liu, Brian Kulis, Jonathan P. How, Lawrence Carin
Trevor Campbell, Miao Liu, Brian Kulis, Jonathan P. How, Lawrence Carin
[algorithm, step, current, setting, ddp, conference, exp, converge] [accuracy, learning, based, international, work, weight, tracking, dataset] [cluster, clustering, inference, nkt, update, zit, assignment, evolving, revived, yit, synthetic, computation, takeoff, science, plane, represents, transitioned] [number, random, comparison, distance, analysis, stochastic] [time, data, sampling, mixture, parameter, dirichlet, gibbs, process, particle, model, prior, gaussian, bayesian, asymptotic, variational, figure, aircraft, observation, distribution, sample, equation, three, computational, posterior, limit, nonparametric] [cost, set, label, point, function, machine, statistical, hard, labeling, penalty, construction, monotonically] [dynamic, dependent, timestep, trajectory, temporal, single]
Stochastic Convex Optimization with Multiple Objectives
Mehrdad Mahdavi, Tianbao Yang, Rong Jin
Mehrdad Mahdavi, Tianbao Yang, Rong Jin
[optimal, algorithm, assumption, online, bound, expected, regret, goal, sampled, assume, upper, randomness, attains, pareto, programming, ensure, long, satisfy] [multiple, learning, approach, domain, weight, average] [variable, update] [stochastic, objective, optimization, convex, convergence, dual, rate, high, violation, gradient, standard, bwt, analysis, method, order, constrained, robust, descent, proposed, exactly] [probability, respect, journal, approximate, replaced, university, estimate, distribution, address] [solution, problem, loss, function, theorem, min, machine, set, denote, max, lipschitz, inequality, consider, general, main, note, primal, proposition, linear, operational, constant, risk, decide, approximation, access] [constraint, uniform, estimated, simple, strong, term, subject]
Error-Minimizing Estimates and Universal Entry-Wise Error Bounds for Low-Rank Matrix Completion
Franz Kiraly, Louis Theran
Franz Kiraly, Louis Theran
[algorithm, multiplicative, bound, space, assumption, optimal, logarithmic] [mask, predicted, prediction, reconstruction, denoising, output, level] [path, missing, graph, edge, structure, reconstructible, cycle, partially, compute] [matrix, variance, error, rank, entry, aij, completion, oriented, basis, sign, minimum, algebraic, baij, noisy, optspace, true, norm, nuclear, method, exactly, reconstructed, order] [kernel, estimate, log, three, data, figure, observed, estimation, positive, independent, model, additive, exact] [estimator, set, theorem, unbiased, denote, combinatorial, linear, minimizing, case, consider, squared, estimating, lemma, polynomial, lower, function, proposition, theoretical, framework] [noise, blue, red, single, calculate]
Message Passing Inference with Chemical Reaction Networks
Nils E. Napp, Ryan P. Adams
Nils E. Napp, Ryan P. Adams
[belief, sum, algorithm, called, state, denoted, action, equilibrium, deterministic] [vector, representation, represented] [reaction, factor, chemical, message, network, variable, graph, ggggb, node, product, inference, concentration, gggggggb, mass, dna, represent, implement, passing, associated, graphical, computation, steady, unassigned, loopy, david, compiled, implemented, probabilistic, erik, strand, damped, compilation, incoming, computed, propagation, catalyze, compute, continuously, physical, ical] [random, order, implementation, small, rate, entry] [figure, marginal, probability, component, simulation, distribution, exact, discrete, equation, parameter, form, time] [set, procedure, linear, design] [molecular, correct, neural, change, system, simple]
A Kernel Test for Three-Variable Interactions
Dino Sejdinovic, Arthur Gretton, Wicher Bergsma
Dino Sejdinovic, Arthur Gretton, Wicher Bergsma
[total, appendix, space, sum] [test, based, dataset, embeddings, embedding, approach, table, learning, well, gram, second] [product, third, associated, partition, construct, graphical, mutually] [pairwise, norm, order, matrix, denotes, random, cumulants, canonical, dimensionality, standard, distance, factorization] [independence, interaction, kernel, lancaster, pxy, measure, joint, statistic, dependence, probability, testing, three, characteristic, nonparametric, independent, reproducing, hilbert, figure, distribution, inner, marginal, positive, null, conditional, kpxy, multivariate, detecting, mutual, detect, estimation, central] [signed, case, rkhs, hypothesis, empirical, consistent, dimension, proposition, provide, notion, straightforward, map, statistical, set] [corresponding, dependent, presence, correlation, correct]
Contrastive Learning Using Spectral Methods
James Y. Zou, Daniel Hsu, David C. Parkes, Ryan P. Adams
James Y. Zou, Daniel Hsu, David C. Parkes, Ryan P. Adams
[algorithm, state, difference, goal, sequence, appendix, trade, conference, assume, natural] [learning, learn, vector, generative, approach, word, hidden, feature, large, table, computer] [variable, associated, auc, disjoint, corresponds] [tensor, spectral, method, analysis, entry, recover, number, projection, matrix, accurately, variance, iteration] [background, foreground, contrastive, model, data, topic, mixture, latent, generated, power, chromatin, document, china, moment, markov, modeling, component, usa, emission, figure, probability, corpus, estimation, hmm, economics, independent, sample, process, university, illustrate, estimate, dirichlet, three] [proposition, set, linear, general, consider, statistical, main] [contrast, biological, exploratory, relative, neural, learns]
Lexical and Hierarchical Topic Regression
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik
[setting, movie] [table, level, hierarchical, hierarchy, word, sentiment, amazon, sentence, supervised, negative, based, discover, vocabulary, second, jointly, type, work, better, token] [path, political, restaurant, structure, associated, shlda, lexical, node, tree, variable, agenda, congressional, assigned, chinese, nested, review, assignment, global, product, existing, sitting, group, pcc, combo, framing, slda, assigning, cnew, perspective, inference, factor, baby, science] [number, discussion] [topic, model, document, dirichlet, parameter, probability, draw, distribution, figure, latent, lda, sampling, positive, process, university, corpus, three, prior] [regression, set, mse] [response, single]
How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal
Jacob Abernethy, Peter Bartlett, Rafael Frongillo, Andre Wibisono
Jacob Abernethy, Peter Bartlett, Rafael Frongillo, Andre Wibisono
[price, option, investor, hedging, bound, minimax, pricing, asset, trading, game, sequence, strategy, upper, current, assumption, lim, hedge, assume, european, gbm, expiration, brownian, payoff, goal, totvarconstraint, previous, setting, jump, appendix, scholes, optimal, eventually, black, volatility, abernethy, payout, taylor, total, chosen, future, online, notice, supremum] [large, well, amount, learning] [underlying, path] [stochastic, call, variance, write, number, key, convergence, error, standard, largest, robust] [time, parameter, university, allow, model] [theorem, lemma, result, inf, function, proof, consider, prove, approximation, note, risk, weaker, paper, main, depend, budget, framework, converges, geometric, case, lower] [nature, constraint, described, term, desired, derivation, motion]
Discovering Hidden Variables in Noisy-Or Networks using Quartet Tests
Yacine Jernite, Yonatan Halpern, David Sontag
Yacine Jernite, Yonatan Halpern, David Sontag
[algorithm, failure, share, identify, step, bound] [learning, learn, learned, hidden, test, negative, unsupervised, based, class, approach, triplet, shared] [quartet, structure, variable, network, singly, coupled, parent, depth, sontag, determine, third, halpern, binary, discovering, size, medical, subtracting, diagnosis, allows, subtraction, hauskrecht, tree, factor, candidate] [number, rank, error, method, spectral, order, analysis, tensor, supplementary] [latent, observed, bayesian, sample, parameter, probability, variational, model, figure, joint, data, mixture, three, distribution, discrete, full, mutual, university] [set, bipartite, lemma, polynomial, linear, case, example, complexity, result] [threshold]
Least Informative Dimensions
Fabian Sinz, Anna Stockl, January Grewe, January Benda
Fabian Sinz, Anna Stockl, January Grewe, January Benda
[space, choice, chosen, difference, maximizing] [learning, feature, approach, input, lnp, average, second, direct, extract] [computed, product] [subspace, optimization, method, matrix, gradient, objective, covariance, dimensionality, order, random, minimize, comparing, number, reduction, analysis] [informative, kernel, mutual, distribution, null, hsic, independent, probability, equation, data, estimation, mmd, entropy, figure, lid, triggered, electric, hilbert, estimate, form, measure, journal, reproducing, independence, respect, dependency, residual, poisson, detect, drawn] [problem, function, dimension, machine, case, linear, correctly, integral, empirical, weakly] [spike, neural, maximally, relative, neuron, single, stimulus, population, corresponding, complex]
A Scalable Approach to Probabilistic Latent Space Inference of Large-Scale Networks
Junming Yin, Qirong Ho, Eric Xing
Junming Yin, Qirong Ho, Eric Xing
[algorithm, space, natural, sampled, bound, total] [large, representation, accuracy, table, based, approach, prediction, bag, better, compared, work] [triangular, network, mmsb, inference, role, triangle, local, eijk, open, scalable, link, global, synthetic, real, ijk, mmtm, runtime, vertex, ptm, social, size, parsimonious, heldout, stanford, update, distinct, edge, degree, motif, methodmmtm, gibbsptm, gibbsmmsb, represents] [stochastic, gradient, method, number, convergence, recovery, high, true, magnitude] [latent, variational, data, model, probability, time, gibbs, three, journal, figure, posterior, parameter, modeling] [batch, set, closed, lower, approximation, machine, complexity, statistical, converges, equivalence, hard] [term]
Adaptive dropout for training deep neural networks
Jimmy Ba, Brendan Frey
Jimmy Ba, Brendan Frey
[algorithm, belief, conference, free, achieves] [hidden, dropout, standout, learning, training, deep, trained, unit, mnist, feature, performance, norb, unsupervised, relu, discriminative, layer, input, compared, test, technique, shallow, momentum, mask, better, weight, achieved, learnt, activation, randomly, object, class, well, good, boltzmann, computer, improve, large, second, denoising, learn, dae, dataset, extracted, international] [network, binary, variable] [method, rate, error, sparse, standard, number, regularization, stochastic] [probability, data, distribution, posterior, figure, model, parameter, including, bayesian, approximate, process, likelihood] [set, function, machine, logistic, linear, result] [neural, described, viewed, produce, activity]
Efficient Online Inference for Bayesian Nonparametric Relational Models
Dae Il Kim, Prem Gopalan, David Blei, Erik Sudderth
Dae Il Kim, Prem Gopalan, David Blei, Erik Sudderth
[online, previous, natural, best, focus, bound] [learning, multiple, hierarchical, based, approach, well, large, learned, work, compare] [community, inference, pruning, relational, node, global, network, perplexity, edge, membership, ahdpr, synthetic, elbo, assortative, edgesperplexity, local, assignment, ammsb, littlesis, yij, truncation, auc, undirected, allows, relativity, pair, scalable, initialization, mixed, unbounded, link, associated, update, mass, graph, associate, degree, hdpr, pruned, nested, toy] [stochastic, number, sij, true, small, gradient] [variational, model, latent, observed, dirichlet, process, nonparametric, distribution, figure, probability, posterior, naive, allow, estimate, sampling, data, restricted] [set, structured] []
Adaptivity to Local Smoothness and Dimension in Kernel Regression
Samory Kpotufe, Vikas Garg
Samory Kpotufe, Vikas Garg
[space, assume, optimal, bound, adaptive, bounded, assumption, notice, algorithm, apply, changing, selecting] [metric, bandwidth, work, training, adapt, approach, input, output] [local, global, size, neighborhood, requirement, balance, diameter] [unknown, variance, high, error, method, analysis, statement] [probability, kernel, estimate, figure, selected, locally, sample, nonparametric, marginal, parameter, assumed] [lemma, regression, dimension, result, procedure, smoothness, main, problem, general, point, suppose, function, denote, proof, adaptivity, selection, eyjx, consider, vary, inequality, argument, note, notion, exists, close, theorem, stability, lepski, theory, hypothetical, depending, cover, adapts, set, argue, union, bias, proper] [intrinsic, simultaneously, change, term, viewed, corresponding]
Optimization, Learning, and Games with Predictable Sequences
Sasha Rakhlin, Karthik Sridharan
Sasha Rakhlin, Karthik Sridharan
[player, regret, algorithm, mirror, step, sequence, predictable, optimistic, minimax, online, game, round, adaptive, programming, observe, flow, play, bound, partial, upper, apply, playing, fact, converge, equilibrium, previous, arbitrary, setting, bounded, assume] [learning, second, vector] [mixed, update, size, extra, factor] [convex, optimization, descent, rate, number, argmin, method, matrix, gradient, small, application, order] [time, exponential, log, approximate, draw, entropy] [problem, lemma, inf, smooth, function, consider, max, set, result, complexity, suppose, case, solution, structured, procedure, simply, corollary, theory, version, provide, idea, linear, notion, point, prox, question, constant] [simple, uniform]
Approximate inference in latent Gaussian-Markov models from continuous time observations
Botond Cseke, Manfred Opper, Guido Sanguinetti
Botond Cseke, Manfred Opper, Guido Sanguinetti
[algorithm, assume, free, fact, notice] [approach, well, box, type] [inference, diffusion, computed, update, parallel, propagation] [canonical, stochastic, matrix, standard, supplementary, order, iteration, method] [time, continuous, process, gaussian, discrete, approximate, marginal, posterior, model, xtk, equation, likelihood, limit, prior, variational, exact, panel, latent, cseke, log, figure, expectation, marginals, form, multivariate, data, discretisation, processing, observed, journal, opper, sampling, modelling, distribution, family, heskes, university, discretised, zammit, moment] [point, function, loss, differential, general, consider, approximation, example, machine, linear, density, formulation, corrected, statistical, problem] [neural, corresponding, spike, left, term]
Linear Convergence with Condition Number Independent Access of Full Gradients
Lijun Zhang, Mehrdad Mahdavi, Rong Jin
Lijun Zhang, Mehrdad Mahdavi, Rong Jin
[algorithm, optimal, step, assumption, bound, assume, deterministic, sum, sequence, named, making, unconstrained, conference] [work, domain, learning, table, applied, based, average, achieve] [mixed, reduce, update, size] [stochastic, gradient, optimization, convex, number, objective, descent, convergence, iteration, emgd, oracle, rate, epoch, method, kwt, sdca, sag, proposed, order, call, random, siam, running, computing, rithm, kbw, matrix, analysis] [full, log, computational, probability, journal, data, university, respect, independent] [function, complexity, condition, smooth, linear, solution, problem, machine, access, lower, theorem, case, lemma, smoothness, consider, approximation, cost, composite, lipschitz, minimizing, set, point, general, loss] [needed, novel, cambridge]
Multi-Task Bayesian Optimization
Kevin Swersky, Jasper Snoek, Ryan P. Adams
Kevin Swersky, Jasper Snoek, Ryan P. Adams
[strategy, expensive, algorithm, best, uncertainty, gain, assume, space, online, previous] [task, learning, average, fold, hyperparameter, svhn, multiple, approach, evaluating, dataset, primary, acquisition, applied, large, knowledge, stbo, validation, scratch, evaluation, mtbo, cheaper, evaluate, training, feature, dynamically, usps, unit, better, based, baseline, mnist] [search, global, reduce, candidate] [optimization, error, objective, order, number, minimum, optimizing, standard, matrix, additional, small] [bayesian, model, gaussian, figure, entropy, hyperparameters, time, auxiliary, estimate, distribution, latent, university, observation, prior, process, grid, full] [function, machine, set, point, cost, framework, query, problem, consider, min] [neural, location, single]
Multilinear Dynamical Systems for Tensor Time Series
Mark Rogers, Lei Li, Stuart Russell
Mark Rogers, Lei Li, Stuart Russell
[stock, sequence, called, algorithm, state, complete, setting] [prediction, vector, video, applied, dataset, consists, trained, initialized] [probabilistic, product, real, synthetic, factor, distributed, member, size, structure] [tensor, matrix, projection, decomposition, number, dimensionality, factorization, error, analysis, tucker, mode, covariance, convergence, standard, random, factorizable, true, alternating] [model, mlds, time, lds, multilinear, latent, series, data, distribution, figure, likelihood, transition, normal, marginal, mat, modeling, bayesian, tesla, element, observation, expectation, rij, sliceerror, conditional, imjm, estimate, tion, drawn, respect, kronecker, ocean, volume] [set, case, complexity, general, function, consider, lemma] [dynamical, system, noise, ieee]
Restricting exchangeable nonparametric distributions
Sinead A. Williamson, Steve N. MacEachern, Eric Xing
Sinead A. Williamson, Steve N. MacEachern, Eric Xing
[sequence, total, arbitrary, sum, focus] [directly, feature, appropriate, better, text, negative, approach, table] [beta, represent, synthetic, binary, structure, law, distributed, atom] [number, row, random, matrix, column, error] [distribution, data, ibp, exchangeable, latent, model, restricted, process, predictive, conditional, zik, bernoulli, probability, restricting, poisson, family, indian, buffet, posterior, sample, exhibited, unrestricted, finetti, nonparametric, binomial, interpretable, equation, parameter, processing, allow, restrict, sampling, figure, restriction, university, measure, exchangeability, mixture, conditioned, gibbs, truncated, gaussian] [point, example, support, ball, set, construction, consider, subset, note, theorem, general, proposition] [described, neural, completely, corresponding]
Forgetful Bayes and myopic planning: Human learning and decision-making in a bandit setting
Shunan Zhang, Angela J. Yu
Shunan Zhang, Angela J. Yu
[optimal, reward, bandit, belief, decision, arm, policy, expected, exploration, choice, best, previous, highest, choosing, future, sequential, algorithm, chooses, current, wsls, exploitative, explore, making, exploitation, total, option, gain, state, horizon, choose, special] [learning, dbm, knowledge, based, performance, people, average, task, better, second] [beta, science] [number, gradient, rate, standard, pairwise] [model, prior, data, probability, bayesian, figure, likelihood, posterior, assumes, distribution, computational, time, predictive, journal, bernoulli] [solution, complexity, problem, statistical] [human, trial, agreement, dynamic, behavior, behavioral, cognitive, control, simulated, assuming, term, estimated, experimental, early, myopic, stay, change, correct]
Probabilistic Movement Primitives
Alexandros Paraschos, Christian Daniel, January Peters, Gerhard Neumann
Alexandros Paraschos, Christian Daniel, January Peters, Gerhard Neumann
[controller, optimal, state, conference, policy, execution, step, reinforcement, introduce] [learning, vector, approach, international, target, multiple, learned, representing, learn, representation, activation, weight, illustrated, second] [probabilistic, conditioning, represents, product, allows] [variance, basis, phase, covariance, matrix, stochastic, order, denotes, exactly] [distribution, time, figure, model, gaussian, probability, joint, generated] [framework, set, machine, linear] [movement, trajectory, robot, control, desired, promp, promps, feedback, noise, system, modulation, rhythmic, combination, primitive, single, reach, blending, speed, blue, motor, varying, red, robotics, behavior, position, match, shaded, encode, temporal, crucial, ten, angle]
Policy Shaping: Integrating Human Feedback with Reinforcement Learning
Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles Isbell, Andrea L. Thomaz
Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles Isbell, Andrea L. Thomaz
[reward, action, policy, optimal, reinforcement, agent, state, mdp, goal, best, provided, algorithm, food, knox, exploration, assume, environment, worse] [learning, domain, approach, amount, work, performance, table, direct, performed, baseline, better, multiple, average, well, negative] [underlying] [number, true, robust, standard, oracle, updated, method] [estimate, probability, parameter, time, figure, grid, distribution, bayesian] [case, consistency, set, function, paper, water, machine, selection, problem] [feedback, human, bql, advise, control, shaping, frogger, reduced, biasing, moderate, sharing, inconsistent, infrequent, estimated, manually, integrating, ideal, signal, modify, produced, frequency]
Linear decision rule as aspiration for simple decision heuristics
Ozgur Simsek
Ozgur Simsek
[decision, cumulative, choose, natural, choosing, difference, making] [datasets, accuracy, object, weighting, performance, type, training, randomly, learned, unit, large, work] [binary, median] [number, error, order, regularization, comparison, rate, analysis, high] [base, figure, approximate, model, parameter, three, university, selected, estimate, positive] [linear, dom, approximation, criterion, approx, statistical, note, consider, depend, theory, max] [rule, dominance, simple, cue, lexicographic, noncompensatory, blue, numeric, environmental, relative, prevalence, corresponding, noncompensation, red, proportion, ranged, attribute, oxford, noncompensatoriness, higher, identical, psychological, behavior, cum, cognitive, refer, paired, examine, gigerenzer, dominates]
Online PCA for Contaminated Data
Jiashi Feng, Huan Xu, Shie Mannor, Shuicheng Yan
Jiashi Feng, Huan Xu, Shie Mannor, Shuicheng Yan
[online, algorithm, initial, previous, revealed, step, current, space, singapore, sampled, robustness, observe, sequence, provided, satisfy, total] [performance, large, based, learning, work, scale, propose, affect] [update, size, accepted, randomized, probabilistic, concentration, supported] [pca, robust, rpca, principal, proposed, authentic, outlier, small, fraction, method, incremental, rpcaonline, matrix, standard, variance, analysis, subspace, covariance, high, newly, number, updating, groundtruth, error, true, contaminated, arxiv, sequentially, preprint, sparse, supplementary, direction, mild, hrpca] [estimation, data, sample, component, process, time, national, figure, sampling] [batch, lemma, theorem, solution, case, set, proof, result, provide, ratio, converges, breakdown, theoretical, subset, point] [signal, noise, department]
Deep content-based music recommendation
Aaron van den Oord, Sander Dieleman, Benjamin Schrauwen
Aaron van den Oord, Sander Dieleman, Benjamin Schrauwen
[conference, msd, play] [music, audio, convolutional, usage, song, learning, deep, dataset, representation, approach, international, similarity, feature, predict, recommendation, large, trained, predicted, wmf, metric, jonas, traditional, recommending, predicting, vector, daft, content, punk, prediction, table, coldplay, semantic, train, training, listened, learned, well, evaluate, affect, enjoy, brian, implicit, mcfee, based] [factor, size, recommender, computed, variable, network, auc, weighted] [collaborative, matrix, objective, factorization, popular, gap, error] [latent, data, model, topic, processing] [regression, linear, subset, problem, machine, rely, map] [neural, user, retrieval, corresponding, preference]
PAC-Bayes-Empirical-Bernstein Inequality
Ilya O. Tolstikhin, Yevgeny Seldin
Ilya O. Tolstikhin, Yevgeny Seldin
[bound, expected, tighter, upper, seldin, bounded, interesting, setting, yevgeny, apply, space, errortest, provided, seeger, advantage] [learning, technique, bounding, prediction, average, based, datasets, vector, work, generalization, test, second] [synthetic, concentration, binary, supported, smaller] [variance, small, analysis, random, comparison, high, order, divergence, supplementary] [probability, distribution, sample, posterior, bayesian, draw, figure, gibbs, equation, data, prior] [inequality, loss, theorem, empirical, note, hypothesis, proof, regression, result, machine, function, john, uci, denote, ratio, provide, ball, case, derive, example, radius, sizeexpected, risk, hold] [greater, term, simultaneously, rule, presented]
Point Based Value Iteration with Optimal Belief Compression for Dec-POMDPs
Liam C. MacDermed, Charles Isbell
Liam C. MacDermed, Charles Isbell
[belief, decpomdp, algorithm, agent, policy, action, state, pomdp, best, utility, optimal, integer, conference, decentralized, strategy, current, decpomdps, decision, bounded, game, converted, previous, choose, multiagent, perseus, reward, sequence, discount, mediator, benchmark, autonomous, cbgs, anfce, horizon, backup, cooperative, history, pure, factored, space, free] [compression, international, improve, large, original, mapping, based, view, box] [existing, factor, underlying, search, merge] [number, solving, solve, iteration, phase, order, method, standard] [bayesian, observation, distribution, probability, joint, independent] [set, function, problem, program, linear, equivalent, approximation, solution] [continuation, dynamic]
Matrix Completion From any Given Set of Observations
Troy Lee, Adi Shraibman
Troy Lee, Adi Shraibman
[algorithm, bound, initial, optimal, assumption, proved, denoted, chosen, bounded, partial, deterministic, apply, revealed, choose] [output, target, generalization, second, performance, approach, vector, good] [real, product, motivates] [matrix, norm, trace, rank, completion, distance, random, dual, error, qij, sign, singular, agrees, minimum, pij, order, exactly, submatrix, minimize, incoherence, candes, noisy, retrieve] [probability, distribution, measure, sample, observed, exact, equal, respect, figure, lowest] [complexity, theorem, set, subset, problem, general, satisfying, max, min, denote, technical, prove, answer, version, result, minimal, consider, program, condition, linear, select, example, proxy, impossible, note, generalized] [property, recall]
Online Learning with Costly Features and Labels
Navid Zolghadr, Gabor Bartok, Russell Greiner, András György, Csaba Szepesvari
Navid Zolghadr, Gabor Bartok, Russell Greiner, András György, Csaba Szepesvari
[algorithm, regret, learner, online, round, bound, observing, probing, assume, space, lnnt, pay, best, bounded, special, option, achieves, expert, called, apply, goal, optimal, mannor, elp, choosing, conference, delayed, alberta] [learning, prediction, vector, feature, weight, based, predict, work, well] [purchase, priori, graph] [number, quadratic, denotes, standard, order, rate, requires] [exponential, distribution, probability, dependence, time, estimate, sampling] [loss, cost, case, problem, linear, function, label, predictor, consider, set, theorem, constant, note, lower, subset, exists, shamir, lipschitz, purchased, complexity, paper, indicator, covering, denote, discretization, construction, general, unbiased] [study]
Sparse nonnegative deconvolution for compressive calcium imaging: algorithms and phase transitions
Eftychios A. Pnevmatikakis, Liam Paninski
Eftychios A. Pnevmatikakis, Liam Paninski
[assume, total, expected] [vector, approach, image, large, reconstruction, multiple, traditional] [concentration, binary, induced, relation] [number, matrix, sparse, true, compressive, convex, compressed, phase, random, nonnegative, sparsity, method, basis, high, standard, error, analysis, required, recovery, singular, proposed] [estimate, probability, time, transition, observed, prior, log, length] [case, problem, statistical, solution, dimension, general, framework, linear, note, result, constant, empirical, point, cone, map, protocol] [imaging, calcium, sensing, spatial, timestep, spike, neural, estimated, neuron, snr, signal, noiseless, voxels, temporal, fully, spiking, undersampling, deconvolution, nature, examine, location, curve, study, cgt, normalized, microscopy, depends, described]
A Stability-based Validation Procedure for Differentially Private Machine Learning
Kamalika Chaudhuri, Staal A. Vinterbo
Kamalika Chaudhuri, Staal A. Vinterbo
[algorithm, best, apply, observe, provided, chosen, goal] [validation, training, learning, score, performance, output, train, good, based, generic, well, second, work, large, performed, input] [existing, auc, size, list] [random, convex, regularization, number, regularized, small, standard, optimization, objective, supplementary, practical] [parameter, data, respect, histogram, differ, figure, tion, exponential, model, alternative] [private, differentially, privacy, procedure, set, stability, differential, machine, linear, condition, density, theorem, loss, budget, logistic, adult, function, design, provide, statistical, case, regression, regularizer, denote, magic, perturbation, notion, select, hinge, result, composition] [single, change, control, experimental, ramp]
A Novel Two-Step Method for Cross Language Representation Learning
Min Xiao, Yuhong Guo
Min Xiao, Yuhong Guo
[algorithm, projected] [language, learning, unlabeled, cross, tsl, text, target, feature, semantic, bilingual, sentiment, representation, word, labeled, multilingual, vocabulary, based, training, monolingual, domain, indexing, english, performance, vector, translation, task, exploiting, represented, outperforms, average, test, concatenated, learn, baseline, efb, german, amazon, approach] [parallel, missing, source, product, perform] [matrix, method, proposed, gradient, descent, completion, analysis, convex, standard, number, row, projection, mij, optimization, operator, small] [data, document, latent, observed, three, figure, model] [set, problem, machine, function] [induce, chose, produce, adaptation]
Capacity of strong attractor patterns to model behavioural and cognitive prototypes
Abbas Edalat
Abbas Edalat
[assume, sum] [large, average, temperature, learning, technique, second, learned, boltzmann, compared] [network, degree, heuristic, hand, symmetry, distributed, real, law] [random, standard, number, method, square, convergence, stochastic, updating, exceeds, solve, solving, basic, error, computing, order] [equation, model, independent, distribution, probability, equal, positive, parameter, figure] [case, solution, theorem, theory, function, spin, stability, lemma, result, consider, general, constant, condition] [strong, pattern, capacity, replica, neural, storage, mathematical, simple, tanh, single, stored, retrieving, presence, attachment, behavioural, critical, memory, rule, attractor, erf, side, multiply, load, mathematically, correlated, recall, identically]
B-test: A Non-parametric, Low Variance Kernel Two-sample Test
Wojciech Zaremba, Arthur Gretton, Matthew Blaschko
Wojciech Zaremba, Arthur Gretton, Matthew Blaschko
[setting, choice, sum, apply, space] [type, test, average, gram, table, large, based, approach, multiple, experiment, feature, better] [size, median, computation, synthetic, computed] [error, number, variance, block, matrix, convergence, distance, method, order, averaging, high, minimum, rate, pairwise] [kernel, distribution, null, sample, gaussian, figure, data, mmdu, asymptotic, central, limit, bootstrap, estimate, testing, time, power, probability, mmdl, statistic, family, mmd, inner, computational, normal, pearson, blocktype, alternative, equation, independent, remains, gamma, measure] [empirical, theorem, hypothesis, set, approximation, selection, consistent, asymptotically, maximum, implies, complexity, converges, lower, statistical, estimating, function] [single, presented, mathematical, increase]
q-OCSVM: A q-Quantile Estimator for High-Dimensional Distributions
Assaf Glazer, Michael Lindenbaoum, Shaul Markovitch
Assaf Glazer, Michael Lindenbaoum, Shaul Markovitch
[algorithm, decision, introduce, expected, sequence, assume, space] [hierarchical, test, coverage, level, average, evaluated, trained, training, performance, learning, vector, introduced, hierarchy, multiple] [global, parallel, decrease] [method, number, averaged, dual, largest, outlier, objective] [data, distribution, equation, estimate, kernel, figure, estimation, probability, gaussian, hilbert] [ocsvm, quantile, program, solution, set, function, ratio, approximated, generalized, hmve, density, estimator, converges, uci, statistical, empirical, quantiles, ocsvms, suggested, support, provide, estimating, hyperplanes, note, lying, optimality, repository, generalize, solved, theoretical, paper, primal, john] [single, estimated, contrast, proportion]
Mid-level Visual Element Discovery as Discriminative Mode Seeking
Carl Doersch, Abhinav Gupta, Alexei A. Efros
Carl Doersch, Abhinav Gupta, Alexei A. Efros
[algorithm, space, previous, goal, adaptive] [visual, patch, bandwidth, dataset, discriminative, purity, feature, image, coverage, large, negative, work, detection, top, retrained, based, approach, discovery, learning, object, level, performance, multiple, well, svm, paris, street, divide, hog, training, denominator, unsupervised, maximize, visually, sidewalk, discover] [local, cluster, clustering, compute, mining, factor, nearest, perform, smaller] [number, gradient, ascent, method, mode, distance, proposed, standard, optimization, dimensionality, norm] [figure, data, element, lda, positive, kernel, distribution, include, analogous] [density, set, ratio, select, note, constant, lower, formulation] [scene, single, left, produce, higher]
Non-Linear Domain Adaptation with Boosting
Carlos J. Becker, Christos M. Christoudias, Pascal Fua
Carlos J. Becker, Christos M. Christoudias, Pascal Fua
[decision, space] [domain, learning, training, approach, feature, target, labeled, task, shared, learn, performance, common, boosting, large, acquisition, weak, segmentation, applied, boosted, image, test, challenging, well, supervised, aerial, trained, mapping, representation, jmlr, transformation, datasets, illustrated, amount, undergone, negative, outperforms, multiple, object] [source, path, tree, split] [method, leverage, gradient, number, unknown, minimize, projection, error, seek] [data, kernel, boundary, latent, model, road, full, histogram, positive, figure] [problem, linear, set, regression, case, loss, function, consider, maximum, solution] [adaptation, single, highly, olfactory]
Exact and Stable Recovery of Pairwise Interaction Tensors
Shouyuan Chen, Michael R. Lyu, Irwin King, Zenglin Xu
Shouyuan Chen, Michael R. Lyu, Irwin King, Zenglin Xu
[algorithm, optimal, step, movie, sum, special, sampled, partial, assume, apply] [performance, level, original, table, training, dataset, recommendation, large, work, tag] [degree, size, truncation, scalable, missing] [tensor, recovery, pairwise, matrix, noisy, rank, completion, convex, recover, number, error, singular, recovered, nuclear, optimization, norm, method, solving, recovering, constrained, svd, order, factorization, tijk, svt, bjk, operator, collaborative, uniformly, aij, denotes, standard, exactly, minimize] [interaction, exact, figure, time, observation, observed, model] [problem, program, solution, shrinkage, set, theorem, guarantee, result, minimization, minimizes, note, exists, suppose, easy, proposition, case, prove, theoretical, proof, general] [noise, temporal, stable, absence, relative, subject]
On Decomposing the Proximal Map
Yao-Liang Yu
Yao-Liang Yu
[sum, assume, goal, interesting, proved, apply] [learning, class, work, feature, domain, multiple] [increasing, compute, group, scaling, combine, collection] [norm, decomposition, convex, remark, symmetric, permutation, recover, sparse, key, order, denotes, siam] [journal, positive, restricted, continuous, additive] [proximal, map, corollary, theorem, function, dom, condition, case, subdifferential, proposition, note, invariance, implies, consider, example, clearly, set, proof, easily, iff, gauge, closed, main, composition, easy, regularizer, prove, exists, result, verify, paper, min, appeared, cone, hilbertian, constant, depend, convexity, hold, weaker, machine, nonsmooth, nontrivial, orthonormal, homogeneous, formula, linear, combettes, yaoliang, clear, indicator] [equality, implication, individual, simple, completely, trivial]
Polar Operators for Structured Sparse Estimation
Xinhua Zhang, Yao-Liang Yu, Dale Schuurmans
Xinhua Zhang, Yao-Liang Yu, Dale Schuurmans
[algorithm, appendix, optimal, current, space] [class, domain, approach, dictionary, demonstrate, unit, accuracy] [path, group, compute, variable, computed, network, local, computation, allows, edge, totally, atomic, corresponds, develop] [sparse, convex, optimization, operator, computing, norm, method, matrix, gradient, reduction, solving, sparsity, objective, number, faster, nonnegative, extend, proposed] [time, form, latent, data, computational, smoothing, figure, model, piecewise, three, log, accurate, conditional] [polar, gcg, linear, function, structured, regularizers, set, cost, max, fused, lasso, apg, consider, solution, note, problem, gauge, arg, case, proximal, easy, regularizer, secant, proposition, main, combinatorial, dom, tum, general, expressed, submodular, min, denote, subset] [simple, coding, corresponding, reduced, constraint]
A Gang of Bandits
Nicolò Cesa-Bianchi, Claudio Gentile, Giovanni Zappella
Nicolò Cesa-Bianchi, Claudio Gentile, Giovanni Zappella
[bandit, algorithm, payoff, contextual, reward, conference, regret, delicious, best, provided, assume, item, assumption] [context, vector, learning, content, recommendation, based, approach, datasets, tested, baseline, work, instance, improve, table, dataset, international, original, created, performance] [node, graph, social, network, cit, recommender, laplacian, smaller, clustering, contained, cluster, associated, update, distributed] [matrix, number, random, running, analysis, order, stochastic, standard, popular, block, high, unknown] [figure, time, independent, model, three, parameter, kernel] [linear, set, machine, multitask, clearly] [user, noise, described, corresponding, control]
Inverse Density as an Inverse Problem: the Fredholm Equation Approach
Qichao Que, Mikhail Belkin
Qichao Que, Mikhail Belkin
[space, setting, sampled, algorithm] [type, learning, shift, performance, unsupervised, test, based, labeled, training, well, table] [] [norm, regularization, optimization, analysis, error, operator, euclidean, method, random, spectral] [kernel, sample, inverse, data, parameter, estimation, sampling, hilbert, gaussian, measure, model, family, estimate, probability, independent, equation] [density, function, problem, ratio, integral, linear, rkhs, covariate, note, set, theoretical, estimating, arg, lsif, tikde, kmm, min, selection, loss, resampling, formulation, empirical, theorem, fredholm, solution, framework, fireq, firep, classical, approximation, version, representer, provide, machine, paper, fire, case, support] [simple, corresponding, assuming]
Robust Image Denoising with Multi-Column Deep Neural Networks
Forest Agostinelli, Michael R. Anderson, Honglak Lee
Forest Agostinelli, Michael R. Anderson, Honglak Lee
[optimal, adaptive, best] [denoising, ssda, image, training, type, trained, corrupted, deep, input, hidden, performance, test, mnist, stacked, speckle, ssdas, better, denoised, weight, tested, output, salt, learning, table, tang, vector, psnr, autoencoder, average, pepper, original, prediction, performed, layer, well, digit, activation, weighting, feature, pixel, good, corrupting, xie, achieved, radiation, dose, unseen] [network, determine, perform, medical, local, mixed] [column, noisy, error, sparse, method, robust, proposed, number, block] [gaussian, figure, data, poisson] [set, linear, function, statistical, border, loss] [noise, neural, signal, single, decoding, uniform, produced, ieee, encoding, performing]
EDML for Learning Parameters in Directed and Undirected Graphical Models
Khaled Refaat, Arthur Choi, Adnan Darwiche
Khaled Refaat, Arthur Choi, Adnan Darwiche
[algorithm, complete, start, initial, optimal, interesting, incomplete, previous] [learning, work, instance, negative, dataset, vector, average, approach, evaluate] [edml, inference, network, unique, graphical, feasibility, undirected, adnan, evidence, variable, originally, cxa, perspective, optimize, computed, probabilistic] [number, iterative, optimization, method, convex, soft, proposed, constrained, gradient, objective, faster] [parameter, bayesian, markov, equation, stationary, log, estimation, data, component, likelihood, conjugate, independent, form, derived, estimate, continuous, respect, approximate] [function, set, point, feasible, case, theorem, procedure, consider, denote, instantiation, example, optimum, problem] [corresponding, subject, constraint]
A Comparative Framework for Preconditioned Lasso Algorithms
Fabian L. Wauthier, Nebojsa Jojic, Michael Jordan
Fabian L. Wauthier, Nebojsa Jojic, Michael Jordan
[algorithm, focus, assume, upper, choosing, choice] [generative, propose, original, compare, instance, traditional] [variable, factor, induced, associated] [recovery, column, basis, preconditioning, comparing, diagonal, standard, supplementary, matrix, proposed, comparison, svd, singular, recover, lead] [parameter, model, gaussian, figure, data, journal, independent, three] [lasso, support, signed, penalty, preconditioned, lemma, selection, pbht, problem, set, theorem, general, hold, framework, paper, note, ratio, empirical, suppose, jia, continue, construction, statistical, case, comparative, rohe, jojic, theoretical, proof, provide, orthonormal, huang, denote] [estimated, noise, relative, depends, thought, left, paul, recall]
A memory frontier for complex synapses
Subhaneil Lahiri, Surya Ganguli
Subhaneil Lahiri, Surya Ganguli
[upper, state, bound, space, initial, equilibrium, subsequent, previous, assume, optimal, quantity] [entire, learning, average, achieve, well, maximize, work, performance] [structure, candidate, develop, understanding, network] [order, number, stochastic, supplementary, decay] [model, time, figure, transition, form, distribution, probability, chain, discrete, markov, process] [theoretical, theory, complexity, general, linear, set, result, function] [memory, synaptic, curve, area, snr, dynamical, potentiation, complex, envelope, molecular, internal, depression, single, described, storage, increase, stored, mpot, scalar, passage, achievable, late, functional, plasticity, potf, population, neuron, neural, early, synapse, simple, change, mathematical, strong, experience, mdep, reach, capacity]
First-order Decomposition Trees
Nima Taghipour, Jesse Davis, Hendrik Blockeel
Nima Taghipour, Jesse Davis, Hendrik Blockeel
[conference, sequence] [based, domain, international, exploiting, performed] [lifted, inference, randvars, isomorphic, node, dpg, probabilistic, propositional, logvars, factor, representative, structure, size, intelligence, dtree, lifting, tree, ground, lve, parfactor, group, grounding, liftable, elimination, counted, represents, width, allows, recursive, compute, interchangeable, prvs, variable, product, randvar, graphical, represent, logical, plm, den, nima, prv, read, leaf, van, guy, jesse, logvar, symmetry, operation, bijection, recursively] [decomposition, number, largest, order, analysis, standard] [model, counting, figure, joint, exact, exponential, form, replacing] [complexity, set, solution, example, result, problem, simply, theorem] [corresponding, single]
Marginals-to-Models Reducibility
Tim Roughgarden, Michael Kearns
Tim Roughgarden, Michael Kearns
[programming, algorithm, optimal, appendix, provided, decision] [class, description, instance, input] [inference, graph, assignment, size, vertex, induced, graphical, compute, network, probabilistic, progress, edge, variable, pair] [number, method, small, oracle, pairwise, dual, random, objective, solving, minimize, solve, reduction, optimization] [marginals, marginal, distribution, data, markov, joint, entropy, time, exponential, full, figure, length, independent] [problem, consistency, linear, consistent, map, polynomial, ellipsoid, separation, support, closest, program, consider, set, theorem, lemma, solved, maximum, function, max, reduces, generalized, algorithmic, primal, general, formulation, main, point, denote, straightforward, prove, provide, simply, suppose] [corresponding, single, reduced, constraint, subject, interest]
Accelerating Stochastic Gradient Descent using Predictive Variance Reduction
Rie Johnson, Tong Zhang
Rie Johnson, Tong Zhang
[option, apply, choose] [learning, training, large, prediction, average, explicit, randomly, view, simpler, test, vector, net, representation, second] [update, computation, larger, stage] [variance, gradient, rate, sgd, svrg, method, convergence, stochastic, convex, sdca, reduction, descent, zhang, standard, fast, optimization, number, roux, error, dual, faster, requires, order, iteration, random, nmnist, coordinate, comparison, require, sag, analysis, regularized, ascent, small, minimum, scheduling, decay] [expectation, figure, residual, parameter, data] [loss, inequality, consider, linear, nonconvex, case, logistic, smooth, set, problem, machine, min, regression, theorem, solution, cost, prove, example, easily, structured] [neural, rule, complex, reduced, memory]
Online Variational Approximations to non-Exponential Family Change Point Models: With Application to Radar Tracking
Ryan D. Turner, Steven Bottone, Clay J. Stanek
Ryan D. Turner, Steven Bottone, Clay J. Stanek
[online, expected, algorithm, bound, complete, black] [tracking, detection, international, performance, accuracy, multiple, improved, compare] [assignment, inference, compute, associated, allows] [measurement, updating, method, standard, number, true] [posterior, data, rice, rcs, bocpd, variational, model, upm, exponential, family, log, distribution, radar, time, association, predictive, length, bayesian, prior, likelihood, exact, track, upms, latent, probability, aircraft, figure, rmse, estimate, conjugate, naive, imm, gaussian, joint, estimation, three, censored, component, marginal, process, sample, series, siap] [point, problem, lower, approximation, example, map, case, technical, machine, paper, derive] [change, clutter, snr]
Optimal Neural Population Codes for High-dimensional Stimulus Variables
Zhuo Wang, Alan Stocker, Daniel Lee
Zhuo Wang, Alan Stocker, Daniel Lee
[optimal, assume, bound, appendix, arbitrary, natural, space] [fisher, input, reconstruction, maximize, work, image, compared, activation] [degree, focused, product] [matrix, covariance, basis, variance, dimensional, optimization, minimize, rate, discussed, det, diagonal, number, scheme, fourier, plotted, high] [gaussian, distribution, prior, mutual, log, independent, model, figure, nonlinear, multivariate, component, university, analytically, marginal, process] [solution, loss, lower, result, problem, constant, simply, case, estimator, general] [neural, stimulus, population, encoding, tuning, diffeomorphic, coding, neuron, infomax, noise, calculate, code, decoding, sin, term, sigmoidal, curve, correlation, sound, unitary, encode, calculation, response, perception, sensory, pennsylvania]
Fast Algorithms for Gaussian Noise Invariant Independent Component Analysis
James R. Voss, Luis Rademacher, Mikhail Belkin
James R. Voss, Luis Rademacher, Mikhail Belkin
[algorithm, step, arbitrary, choice, chosen] [vector, based, second, performance, invariant, work, technique, unit] [update, variable] [ica, order, matrix, random, cumulant, convergence, cumulants, fourth, fast, recover, analysis, gradient, number, robust, fastica, hessian, comparison, method, practical, iteration, whitening, noisy, requires, diagonal, indexica, samplesamari, pca, amari, orthogonalization, unknown, cubic, proposed, column, required, matlab, standard] [independent, gaussian, data, component, latent, observed, distribution, additive, estimate, white, univariate, drawn, equation, process, sample] [case, function, lemma, denote, note, theorem, separation, provide, complexity, paper] [noise, signal, blind, noiseless, neural, identity]
Minimax Theory for High-dimensional Gaussian Mixtures with Sparse Mean Separation
Martin Azizyan, Aarti Singh, Larry Wasserman
Martin Azizyan, Aarti Singh, Larry Wasserman
[bound, minimax, setting, assume, upper, optimal, computationally, expected, algorithm] [learning, feature, precise, computer, work, second] [clustering, relevant, variable, stage, mellon, vempala, symposium] [method, sparse, tan, small, high, spectral, standard, number, dimensional, error, principal, basis, rate, gap, require] [log, mixture, sample, probability, gaussian, gaussians, data, journal, component, distribution, estimation, spherical, university] [proposition, separation, selection, theorem, loss, proof, provide, max, case, complexity, lower, statistical, min, consider, theoretical, estimating, set, function, paper, isotropic, lemma, general, dimension, machine, subset, theoretic, chaudhuri, denote, witten, penalized, santosh, introduction] [sin, depends, simple, relative]
Predicting Parameters in Deep Learning
Misha Denil, Babak Shakibi, Laurent Dinh, Marc'Aurelio Ranzato, Nando de Freitas
Misha Denil, Babak Shakibi, Laurent Dinh, Marc'Aurelio Ranzato, Nando de Freitas
[factored, space, choice, conference, natural, choose] [layer, feature, learning, deep, dictionary, convolutional, hidden, weight, technique, prediction, predict, performance, rica, image, second, approach, trained, work, knowledge, training, predicted, input, scale, pixel, train, reconstruction, learned, visible, representation, architecture, directly, extremely, unsupervised, constructing, well, output, appropriate] [network, structure, size, reduce, connected, distributed, construct, local] [number, column, matrix, random, ridge, covariance, ica] [kernel, figure, parameter, model, prior, processing, data, exponential, full, form] [linear, squared, smoothness, set, paper, intuition, regression, function, case] [neural, dynamic, single, static, interpretation, fully, corresponding, described]
Estimating the Unseen: Improved Estimators for Entropy and other Properties
Paul Valiant, Gregory Valiant
Paul Valiant, Gregory Valiant
[algorithm, total, expected, appendix, bound, optimal, upper] [domain, unseen, approach, vector, large, work, performance, assigns, computer, second] [size, distinct, portion, occur, mass, science, nif] [number, distance, error, true, exactly, small, objective, random, analysis] [sample, distribution, probability, histogram, estimate, entropy, observed, naive, estimation, figure, data, poisson, drawn, independent, zipf, valiant, cae, parameter, mesh, three, returned, element, derived, sampling, likelihood, vopt, accurate] [estimator, linear, support, estimating, program, example, empirical, bub, consider, theoretical, statistical, function, note, set, constant, theorem, proof, hamlet, simplest] [uniform, property, consisting, plausible, contrast, population]
What do row and column marginals reveal about your dataset?
Behzad Golshan, John Byers, Evimaria Terzi
Behzad Golshan, John Byers, Evimaria Terzi
[algorithm, sequential, assume, step, observe, exploration, sum, introduce, computes] [hidden, input, dataset, large, datasets, generative, approach, better, experiment, accuracy, propose, vector, raw, average, jth, table] [binary, compute, size, computed, existing] [column, matrix, pdfs, row, simpleis, dataspace, number, knot, running, entry, computing, error, rasch, pdf, high, nola, implicitly, adjust, method, standard, realization, enumeration] [marginals, sampling, time, probability, estimate, data, model, rest, equation, distribution, prior, figure, sample, mcmc, university, observed, journal] [problem, set, dblp, polynomial, provide, function, statistical, estimating, framework, linear] [refer, cell, described]
One-shot learning by inverting a compositional causal process
Brenden M. Lake, Ruslan Salakhutdinov, Josh Tenenbaum
Brenden M. Lake, Ruslan Salakhutdinov, Josh Tenenbaum
[sampled, abstract, natural, previous, conference, start, algorithm, space] [image, learning, people, hbpl, character, deep, stroke, learn, hierarchical, visual, raw, handwritten, concept, better, boltzmann, computer, learned, type, turing, performance, scale, compared, test, tested, training, class, mechanical, argmax, evaluated] [generate, structure, inference, causal, mit] [analysis, error, number, rate, standard, variance] [model, figure, bayesian, generating, log, spline, distribution, three, drawn, posterior, approximate, grid, background, include, selected, causality, data, including] [machine, set, program, approximation, example] [motor, simple, control, ieee, pattern, neural, single, produce, human, rule]
Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators
Michel Besserve, Nikos K. Logothetis, Bernhard Schölkopf
Michel Besserve, Nikos K. Logothetis, Bernhard Schölkopf
[arbitrary, space, bounded, assume, lim] [test, type, approach, based, visual, well, vector, bottom, compare, performance, concept, similarity, window] [product, lfp, causal] [random, operator, norm, order, analysis, fourier, transform, matrix, pairwise] [time, kernel, series, independence, kcsd, estimate, hsic, figure, markov, biased, hilbert, measure, rbf, processing, dependency, gamma, band, independent, distribution, characteristic, centered, positive, parameter, reproducing, probability, null, bivariate, transition, data, enables] [theorem, statistical, linear, unbiased, density, general, framework, structured, lemma, case, consequence] [neural, frequency, complex, coupling, scalar, dynamical, activity, monkey]
Optimizing Instructional Policies
Robert Lindsey, Michael Mozer, William J. Huggins, Harold Pashler
Robert Lindsey, Michael Mozer, William J. Huggins, Harold Pashler
[policy, space, optimal, duration, strategy, focus, involves, explored, pomdp, goal, exploration, glopnor, grey, outcome] [training, category, learning, experiment, performance, test, traditional, fading, approach, accuracy, based, concept, large, evaluating, propose, evaluation, exemplar, technique, challenge] [search, represents, determine, pair] [optimization, number, noisy, optimizing, distance, method, additional, standard] [figure, gaussian, posterior, process, data, model, time, probability, observed, boundary, alternative, family, estimate] [function, set, design, optimum, label, budget, selection, statistically, teaching, consistent, parameterized, manner] [subject, experimental, instructional, ppf, individual, blocking, gpr, population, trial, student, cognitive, correct, reliable, human, presentation, psychological, indicate]
Integrated Non-Factorized Variational Inference
Shaobo Han, Xuejun Liao, Lawrence Carin
Shaobo Han, Xuejun Liao, Lawrence Carin
[bound, upper, optimal, deterministic, space, assumption, conference] [based, accuracy, compare, evaluated, dataset, sense, learning, quality, hyperparameter] [inference, evidence, global, nested, elbo, parallel] [method, divergence, gradient, number, square, matrix, numerical, proposed, norm, fast] [variational, posterior, bayesian, gaussian, grid, latent, inla, approximate, distribution, marginal, figure, accurate, mcmc, bayes, hybrid, mixture, marginals, model, computational, time, full, parameter, university, hyperparameters, normal, analytically, independent, journal, monte, exact, continuous, expectation, processing, joint] [approximation, lasso, laplace, lower, consider, solution, function, provide, statistical, minimizing, problem, regression, machine, theorem, linear, lemma] [integrated, neural, integration]
More data speeds up training time in learning halfspaces over sparse vectors
Amit Daniely, Nati Linial, Shai Shalev-Shwartz
Amit Daniely, Nati Linial, Shai Shalev-Shwartz
[algorithm, return, upper, bound, natural, item, assumption, pac, learner, choosing, assume] [learning, class, training, learn, large, supervised, task, output, technique, vector, instance, based, learnt, representation] [boolean, size, construct, assignment, supported, generate] [random, sparse, error, standard, small, number] [sample, data, probability, computational, positive, independent, distribution, form] [hypothesis, set, question, hardness, formula, theorem, lower, halfspaces, problem, refuting, proof, conjecture, complexity, exists, denote, answer, clause, improper, example, ratio, note, main, prove, theoretic, hard, impossible, result, case, agnostic, studied, consider, establish, israel, validity, statistical] [learns, consisting, produce]
(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings
Abhradeep Guha Thakurta, Adam Smith
Abhradeep Guha Thakurta, Adam Smith
[regret, algorithm, bandit, online, bound, sum, follow, nonprivate, previous, setting, sequence, leader, appendix, space, adaptive, partial, pftal, adam, satisfy, aggregation, step, cynthia, lipshitz, complete, replace, continual, optimal, variant, oblivious, fact, best, subsequent] [learning, input, work, output, vector, based, class, technique, entire, table, unit] [tree, smaller] [convex, gradient, analysis, quadratic, minimize, random] [time, approximate, full, parameter, data, log, dependence] [private, privacy, function, cost, differential, differentially, set, lower, theorem, loss, version, min, lipschitz, arg, general, consider, provide, approximation, linear, convexity, design, access, machine, ball, note, notion] [change, strong, stream]
Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions
Rishabh K. Iyer, Stefanie Jegelka, Jeff A. Bilmes
Rishabh K. Iyer, Stefanie Jegelka, Jeff A. Bilmes
[bound, algorithm, upper, optimal, follow, previous, tighter, cooperative, sum, logarithmic, apply] [learning, better, class, work, improved, training, concept, learn] [factor, spanning, graph, path] [constrained, cut, number, sparse, matching, minimum, nonnegative, random, optimization, imply] [log, approximate, time, form, figure, family] [submodular, function, approximation, curvature, lower, modular, corollary, lemma, set, monotone, minimization, polynomial, theoretical, combinatorial, problem, empirical, mub, version, concave, minimizing, theorem, approximating, general, tight, maximization, machine, cardinality, polymatroid, submodularity, implies, practically, prove, balcan, provide, main, solution, jegelka, factorn, pmac, surrogate, constant, case, matroid] [varying, normalized, depends, constraint]
Σ-Optimality for Active Learning on Gaussian Random Fields
Yifei Ma, Roman Garnett, Jeff Schneider
Yifei Ma, Roman Garnett, Jeff Schneider
[greedy, satisfy, sum] [learning, unlabeled, class, labeled, outperforms, prediction, directly, accuracy, belonging, work] [graph, node, global, binary, undirected, loo, variable, network, toy, connected, search, larger, mellon] [random, covariance, matrix, objective, variance, reduction, nonnegative, optimization, application, high, number, largest, harmonic, spectral, diag] [predictive, model, gaussian, figure, data, markov, conditional, inverse, university, tion, alternative] [active, risk, grf, grfs, lemma, set, minimization, label, loss, theoretical, query, condition, criterion, optimality, example, machine, minimizes, subset, arg, theorem, function, citation, solution, survey, dblp, suppressor, lij, minimizing, zhu, suppose, regression, surrogate, submodularity, consider, approximation] [correlation, proportion, described, highly]
Learning Kernels Using Local Rademacher Complexity
Corinna Cortes, Marius Kloft, Mehryar Mohri
Corinna Cortes, Marius Kloft, Mehryar Mohri
[algorithm, bound, sum, optimal, bounded, choice, unif, observe, highest] [learning, based, class, tail, performance, multiple, report, svm, training, experiment, compare, generalization, average, test] [local, compute, existing, binary, global] [convex, optimization, standard, mkl, small, order, solving, matrix, trace, analysis, eigenvalue, fast, convergence] [kernel, data, family, probability, figure, journal, measure, base, gaussian] [rademacher, complexity, conv, notion, problem, machine, risk, hypothesis, tss, theorem, loss, function, design, result, theoretical, linear, set, point, case, consider, note, general, empirical, energ, proposition, exon, concave, min, denote] [strong, angle, supplemental, combination, material, determined, constraint]
Causal Inference on Time Series using Restricted Structural Equation Models
Jonas Peters, Dominik Janzing, Bernhard Schölkopf
Jonas Peters, Dominik Janzing, Bernhard Schölkopf
[algorithm, assume] [test, experiment, based, class, jointly, work, temperature, discovery, large] [causal, graph, structure, structural, inference, node, allows, dag, delay] [order, method, lead, true, require, asymmetry, call, number] [time, model, data, series, timino, instantaneous, nonlinear, additive, causality, wrong, independence, full, independent, iid, gaussian, undecided, infers, equation, granger, sample, multivariate, chu, restricted, shifted, pai, hsic, var, include, remains, figure, including, arrow, confounders, length, differ] [linear, theorem, summary, function, case, set, regression, condition, provide, simulate, lemma] [noise, correct, infer, corresponding, code]
Symbolic Opportunistic Policy Iteration for Factored-Action MDPs
Aswin Raghavan, Roni Khardon, Alan Fern, Prasad Tadepalli
Aswin Raghavan, Roni Khardon, Alan Fern, Prasad Tadepalli
[policy, action, opi, factored, state, symbolic, backup, bellman, algorithm, mpi, add, space, diagram, optimal, elevator, impact, decision, bounded, mdps, ring, actionssolution, denoted, computes, spudd, planning, reward, opportunistic, mdp, partial, violate, bottleneck, current, greedy, conference] [evaluation, better, domain, large, work, representation, computer, representing, dbn, compression, represented] [size, variable, pruning, parallel, root, scalability, leaf, structure, relational, person, larger] [iteration, number, running, true, lead, denotes, exceeds] [figure, time, limit, exact, probability, approximate, joint, full, equation] [function, compact, max, denote, procedure, example, sdp, version] [memory, constraint, dynamic, control]
Real-Time Inference for a Gamma Process Model of Neural Spiking
David Carlson, Vinayak Rao, Joshua T. Vogelstein, Lawrence Carin
David Carlson, Vinayak Rao, Joshua T. Vogelstein, Lawrence Carin
[algorithm, online, space, previous, partial] [multiple, well, vector, dictionary, performance, output, compare, truth, based, work, weight, detection] [cluster, inference, associated, ground, distributed, assigned, update, event] [number, rate, random, standard, supplementary, true] [time, process, model, data, poisson, bayesian, posterior, gamma, mixture, distribution, measure, prior, nonparametric, gaussian, drawn, parameter, university, dirichlet, probability, detect, journal, positive, three, residual, panel, figure, allow] [set, approximation, batch, note] [spike, neuron, waveform, overlapping, single, channel, intracellular, shape, spiking, recording, neural, noise, false, activity, electrode, voltage, sorting, marked, threshold, extracellular, earlier, multichannel]
Phase Retrieval using Alternating Minimization
Praneeth Netrapalli, Prateek Jain, Sujay Sanghavi
Praneeth Netrapalli, Prateek Jain, Sujay Sanghavi
[algorithm, step, sampled, natural, setting, variant] [vector, work, based, approach, applied, second, output, image, large, amount, better, good, performance, multiple] [initialization, underlying, correctness] [phase, matrix, alternating, random, phaselift, altminphase, measurement, convex, dist, recovery, standard, number, magnitude, solving, arxiv, key, preprint, sparse, method, convergence, error, solve, phasecut, diagonal, recover, analysis, success, fourier, denotes, recovering, rank, empirically, trace, whp] [log, gaussian, sample, figure, independent, computational, probability, normal] [problem, complexity, minimization, lemma, theorem, theoretical, case, sdp, note, solution, linear, proof, empirical, support, constant, paper, main, consider] [retrieval, complex, signal, greater, imaging]
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko
Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko
[best, conference, natural, movie] [transe, training, learning, embeddings, relationship, embedding, head, test, entity, performance, tail, unstructured, corrupted, table, validation, raw, work, large, trained, award, lfm, knowledge, freebase, prediction, evaluation, vector, appear, learn, good, translation, predicted, well, rescal, scale, mtv, international, word, better, achieve, predict, approach, wordnet, dissimilarity] [link, relational, represent, corresponds, split] [number, rank, matrix, stochastic, method, gradient, factorization, tensor, optimization] [data, model, modeling, latent, selected, processing] [set, dimension, procedure, machine, ranking, lower] [neural]
Generalizing Analytic Shrinkage for Arbitrary Covariance Structures
Daniel Bartz, Klaus-Robert Müller
Daniel Bartz, Klaus-Robert Müller
[assumption, lim, behaviour, optimal, sequence, stock] [large, better, automatic, usps, average, table, performance, target, outperforms, tested, propose] [real, growth, structure, factor] [covariance, standard, matrix, orthogonal, error, largest, eigenvalue, high, number, analysis, dimensionality, regularization, random, variance, additional, small, letter, isolet, convex, low, rate, fourth, order] [data, model, sample, figure, lda, limit, journal, estimation, dependency] [shrinkage, analytic, complement, consistency, dispersion, portfolio, theorem, estimator, statistical, spoken, squared, exists, qda, derive, linear, procedure, prove, theoretical, min, selection, result, arg, eigendirections, lower, constant, tij, cost, machine, eighth, paper] [normalized, combination, left]
Flexible sampling of discrete data correlations without the marginal distributions
Alfredo Kalaitzis, Ricardo Silva
Alfredo Kalaitzis, Ricardo Silva
[algorithm, step, space, deterministic] [learning, approach, level, applied] [factor, compute, variable, structure, pair, smallest, graphical] [matrix, rank, number, standard, constrained, application, method, true, small, dimensionality, mode] [gaussian, sampling, copula, hmc, sample, time, data, discrete, travel, likelihood, distribution, model, latent, marginal, extended, multivariate, figure, truncated, hamiltonian, hough, mcmc, joint, bayesian, monte, chain, mixing, gibbs, univariate, carlo, cdf, conditioned, sampler, posterior, marginals, describe, markov, sinusoid, component, parameter, exact, observed, boundary] [linear, machine, framework, general, case, provide, function, hard, idea, structured, point] [correlation, blue, velocity, position, collision, red, constraint, envelope]
Adaptive Anonymity via $b$-Matching
Krzysztof M. Choromanski, Tony Jebara, Kui Tang
Krzysztof M. Choromanski, Tony Jebara, Kui Tang
[adversary, assume, utility, algorithm, adaptive, succeeds, released, compatible, usernames, ypublic, goal, explored] [level, achieve, handle, output, people, vector, weight, type, better] [graph, compatibility, degree, associated, person, edge, vertex, protection, color, node, social, forest] [anonymity, matching, symmetric, attack, number, random, sustained, entry, matrix, key, minimum, obfuscated, resilience, additional, gij, existence, permutation, asymmetric, method, article] [data, probability, advance, respect, family, perfect, figure, university, allow] [bipartite, privacy, set, case, database, problem, lemma, theorem, consider, relaxation, denote, approximation, provide] [user, single, desired, uniform]
Convex Tensor Decomposition via Structured Schatten Norm Regularization
Ryota Tomioka, Taiji Suzuki
Ryota Tomioka, Taiji Suzuki
[assume, sum, optimal, bound, appendix, deterministic, choice, linearly] [approach, performance, better, predicted, predicts] [group, factor, scaling, singleton, perform] [tensor, overlapped, schatten, rank, decomposition, norm, regularization, convex, mode, unknown, error, true, duality, minimum, matrix, performs, noisy, analysis, theoretically, empirically, optimization, dual, statement, proposed, sparsity, unfolding, siam, mink, completion, basic, tucker, spectral, call] [latent, figure, panel, data, multilinear, series, observation, mixture, gaussian, component, inverse] [complexity, structured, constant, note, inequality, technical, problem, mse, minimization, squared, lemma, theorem, consistency, minimal, solution, theoretical, lasso, loss] [noise, presented, simultaneously, study, depends]
Unsupervised Structure Learning of Stochastic And-Or Grammars
Kewei Tu, Maria Pavlovskaia, Song-Chun Zhu
Kewei Tu, Maria Pavlovskaia, Song-Chun Zhu
[algorithm, gain, natural, previous, initial, action, greedy] [learning, training, approach, image, learned, dataset, language, second, unsupervised, learn, context, video, multiple, based, table, type, better, well, applied, large, represented, representing, target, performance, computer] [grammar, fragment, nonterminal, search, event, atomic, node, terminal, structure, size, existing, third, relation, represents, product, viterbi, represent, perplexity, construct] [stochastic, method, number, order, proposed, iteration] [data, figure, probability, posterior, likelihood, sample, prior, model, testing, restrict, beam] [set, example, agnostic] [pattern, temporal]
Modeling Overlapping Communities with Node Popularities
Prem Gopalan, Chong Wang, David Blei
Prem Gopalan, Chong Wang, David Blei
[algorithm, bound, natural, step, notice] [learning, similarity, better, prediction, accuracy, test, large] [node, community, network, global, mmsb, inference, popularity, link, local, social, pair, strength, elbo, degree, develop, real, update, rab, collaboration, political, blockmodel, netscience, structure, optimize, american, size, probabilistic] [stochastic, amp, gradient, number, random, noisy, precision, small, coordinate, ascent, subsampling, iteration, objective] [variational, model, data, posterior, latent, predictive, respect, figure, estimate, draw, probability, observed, include, sample, journal, conditional, distribution, parameter, likelihood] [set, lower, indicator, unbiased, statistical] [single, capture, overlapping, explain, recall]
Learning from Limited Demonstrations
Beomjoon Kim, Amir massoud Farahmand, Joelle Pineau, Doina Precup
Beomjoon Kim, Amir massoud Farahmand, Joelle Pineau, Doina Precup
[policy, expert, apid, optimal, bellman, lfd, space, algorithm, lspi, demonstration, reinforcement, bound, upper, drl, assumption, state, api, goal, reward, initial, choice, agent, brake, dagger, mdp, current, outperformed, assume, focus, abundant, school, behaviour, canada, acceleration, mcgill, availability, iterationsaverage] [learning, supervised, well, performance, evaluate, large, compare, good, evaluation, approach, average, task, based, computer, margin] [real, science] [error, iteration, optimization, method, number, regularization, random, argmin, standard, distance] [data, approximate, figure, probability, university, estimate, three] [function, set, problem, complexity, turn, max, note, empirical, provide, machine, framework, case, regularizer, consider, linear] [robot, avoid, reach, control, velocity]
On the Complexity and Approximation of Binary Evidence in Lifted Inference
Guy van den Broeck, Adnan Darwiche
Guy van den Broeck, Adnan Darwiche
[conference, bounded, aaai] [learning, international, vector, represented, based, knowledge, technique, large, work] [evidence, boolean, lifted, inference, binary, unary, size, conditioning, bmf, relational, probabilistic, ground, mln, den, van, relation, mcmclifted, lmcmc, perform, guy, kld, web, logical, broeck, intelligence, predicate, webkb, pauli, davis, mining, adding, graphical, compute, represent, divergenceiterationground, lifting] [rank, matrix, factorization, computing, number, reduction, error] [approximate, exact, data, model, figure, mcmc, distribution, probability, marginal, investigate, posterior, full] [complexity, approximation, example, formula, set, condition, statistical, polynomial, theorem, result, problem, machine, consider, outer, main] [corresponding, circuit]
Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
Francis Bach, Eric Moulines
Francis Bach, Eric Moulines
[algorithm, achieves, best, step, optimal, assumption, bound, assume] [test, datasets, performance, learning, training, average, large, achieve, better] [proportional, global, synthetic, size, smaller] [stochastic, averaged, rate, sag, convergence, gradient, newton, sgd, analysis, adagrad, square, quadratic, order, typically, sido, method, alpha, descent, convex, decaying, covertype, denotes, covariance, standard] [log, figure, data, markov, news, chain, expectation, independent, stationary, distribution, journal] [logistic, consider, approximation, constant, loss, point, regression, theoretical, support, note, function, linear, machine, close, convexity, converges, theorem, provide, complexity, effective, problem, denote, condition, excess, technical, proof, smoothness] [strong, control, novel, left, normalized]
Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching
Marcelo Fiori, Pablo Sprechmann, Joshua T. Vogelstein, Pablo Muse, Guillermo Sapiro
Marcelo Fiori, Pablo Sprechmann, Joshua T. Vogelstein, Pablo Muse, Guillermo Sapiro
[algorithm, black, sum, linearized] [original, consists, performance, approach, compared, second, common, measured] [graph, multimodal, inference, group, adjacency, graphical, weighted, real, permuted, synthetic, faq, path, network, bter, elegans, vogelstein, chemical, publicly, underlying] [matching, matrix, permutation, proposed, collaborative, method, covariance, optimization, convex, det, error, solving, random, sparse, naturally, application, glag, number, doubly, analysis, solve] [data, log, inverse, figure, estimation, model, distribution, processing, university, joint] [problem, min, formulation, lasso, version, set, result, arg, case, solved, active, minimizing] [noise, fmri, presented, pattern, connection, experimental, described, brain, term, neural]
Transportability from Multiple Environments with Limited Experiments
Elias Bareinboim, Sanghack Lee, Vasant Honavar, Judea Pearl
Elias Bareinboim, Sanghack Lee, Vasant Honavar, Judea Pearl
[transportability, trmz, limited, conference, calculus, algorithm, diagram, observational, assume, estimand, menlo, interventional, aaai, bareinboim, goal, return, called, lee, previous, formal, special, age] [target, domain, knowledge, multiple, learning, work, test, based] [causal, source, structural, represents, collection, computable, induced, relation, intelligence, heterogeneous, edge, powerful, randomized, rewrite, subgraph, local, graphical, mit, variable, graph] [conducted, transport, call, computing, analysis, order, variance] [data, expression, estimate, national, university, model] [selection, set, theorem, consider, statistical, problem, condition, formula, example, note, procedure, general, provide, machine, corollary, paper, implies] [experimental, relative, rule, desired, infer]
Supervised Sparse Analysis and Synthesis Operators
Pablo Sprechmann, Roee Litman, Tal Ben Yakar, Alexander M. Bronstein, Guillermo Sapiro
Pablo Sprechmann, Roee Litman, Tal Ben Yakar, Alexander M. Bronstein, Guillermo Sapiro
[setting, algorithm, total] [learning, supervised, image, vector, pursuit, dictionary, reconstruction, music, training, transcription, learned, representation, convolutional, piano, well, denoising, performance, approach, achieved, better, metric, input, resolution, discriminative, feature, unsupervised] [network] [analysis, sparse, synthesis, fast, matrix, proposed, optimization, operator, admm, number, gradient, standard, iterative, polyphonic, regularization, solving, projection] [model, exact, data, form, inverse, respect, figure, university, computational, approximate, gaussian, extended] [problem, solution, loss, approximation, set, case, function, linear, consider, note, proximal, proposition, solved, version, map, framework, min] [bilevel, ieee, signal, neural, sensing, minimizer, depends, described]
Generalized Denoising Auto-Encoders as Generative Models
Yoshua Bengio, Li Yao, Guillaume Alain, Pascal Vincent
Yoshua Bengio, Li Yao, Guillaume Alain, Pascal Vincent
[algorithm, bound, apply, walk] [training, denoising, learning, reconstruction, dae, trained, input, score, generative, learned, amount, work, based, deep, rbm, feature] [local, associated] [true, regularized, implicitly, error, operator, small, matrix, random] [distribution, corruption, chain, markov, data, sampling, walkback, asymptotic, process, model, conditional, gaussian, manifold, generated, figure, sample, spurious, joint, contractive, limit, continuous, estimation, generating, marginal, estimate, likelihood, log, transition, probability, observed] [estimator, function, energy, consistent, density, converges, procedure, example, note, generalized, result, consider, criterion, minimizing, case, theorem, maximum, machine, idea, set] [noise, neural, estimated, interpretation, simple, capture]
Documents as multiple overlapping windows into grids of counts
Alessandro Perina, Nebojsa Jojic, Manuele Bicego, Andrzej Truski
Alessandro Perina, Nebojsa Jojic, Manuele Bicego, Andrzej Truski
[conference, algorithm, share, choose, space, best, modeled] [window, word, generative, text, based, bag, learning, learned, represented, embedding, dataset, multiple, evaluated, semantic, large, computer, usage, similarity, international] [size, characterized, generate, represents] [number, small, pick, standard, basic, analysis] [grid, counting, model, componential, distribution, lda, topic, latent, kernel, dirichlet, generated, ccgs, document, ccg, log, data, probability, mixture, modeling, component, pizza, equal, considered, multinomial, prior, figure, sample, sam, admixture, three, journal, allocation, spherical] [effective, linear, machine, set] [location, ieee, position, capacity, pattern, moving, area, highly, simple, described, thought]
Solving the multi-way matching problem by permutation synchronization
Deepti Pachauri, Risi Kondor, Vikas Singh
Deepti Pachauri, Risi Kondor, Vikas Singh
[algorithm, satisfy, natural, long, space] [image, large, computer, multiple, baseline, object, representation, work, supervision, feature, accuracy, based, approach, recognition, dataset, building, correspondence, common] [matchings, graph, assignment, structure, degree, ground, hand, mutation, house] [permutation, matching, matrix, synchronization, eigenvectors, pairwise, method, error, landmark, random, symmetric, orthogonal, leading, recover, tji, solving, eigenvalue, number, stereo, eigenvector, rank, array, distance, fig, column, small] [figure, form, probability, distribution] [problem, set, linear, note, proposition, solved, consistent, relaxation, arg, consistency, consider, condition, cost, paper, combinatorial] [correct, noise, normalized, shape, stable, rotation]
Robust Bloom Filters for Large MultiLabel Classification Tasks
Moustapha M. Cisse, Nicolas Usunier, Thierry Artières, Patrick Gallinari
Moustapha M. Cisse, Nicolas Usunier, Thierry Artières, Patrick Gallinari
[algorithm, best] [predicted, approach, large, training, prediction, datasets, test, learning, compared, frequent, based, improve, scale, appear, predict, performed] [bloom, size, representative, cluster, bit, mlc, binary, exclusive, mutually, incorrectly, multilabel, clustering, smaller, inference, plst, disjunctive, uhl] [number, hash, method, standard, robust, hamming, random, scheme, reduction, small, compressed, rate, error] [figure, positive, computational, probability, data, distribution, time] [label, set, loss, complexity, design, ratio, example, subset, cardinality, main, denote, theoretical] [encoding, decoding, code, false, single, strong, encode]
Visual Concept Learning: Combining Machine Vision and Bayesian Generalization on Concept Hierarchies
Yangqing Jia, Joshua T. Abbott, Joseph Austerweil, Thomas Griffiths, Trevor Darrell
Yangqing Jia, Joshua T. Abbott, Joseph Austerweil, Thomas Griffiths, Trevor Darrell
[sampled, previous, total, space] [concept, learning, visual, generalization, vision, image, word, level, performance, perceptual, object, imagenet, dataset, task, work, learn, training, test, large, people, conventional, challenge, truth, score, baseline, hierarchy, instance, confusion, ilsvrc, validation, negative, compare, randomly, average, approach, better, tenenbaum, constructing] [node, leaf, existing, size, ground, subtree, science] [number, proposed, method, basic, precision, matrix, gradient] [bayesian, figure, probability, three, model, positive, prior, data, describe] [set, query, machine, hypothesis, example, note, problem, provide] [human, system, novel, cognitive, psychological]
Dirty Statistical Models
Eunho Yang, Pradeep Ravikumar
Eunho Yang, Pradeep Ravikumar
[sum, bound, assumption, previous] [multiple, work, class, well, instance, applied] [structural, structure, size, pair] [regularization, matrix, subspace, error, norm, sparse, analysis, principal, covariance, high, typically, key, robust, number, convex, incoherence, convergence, row, frobenius, exactly, elementwise, regularized, random, constrained, solve, decomposition] [parameter, model, log, component, respect, observation, probability, hybrid, restricted, sample, estimation, gaussian] [theorem, function, statistical, linear, suppose, consider, regression, loss, set, problem, condition, corollary, provide, superposition, decomposable, structured, general, proposition, framework, note, varied, max, derive, min, solution] [corresponding, strong, term, noise]
Locally Adaptive Bayesian Multivariate Time Series
Daniele Durante, Bruno Scarpa, David Dunson
Daniele Durante, Bruno Scarpa, David Dunson
[online, algorithm, state, adaptive, space, step, stock] [approach, dictionary, performance, second, dataset, based, well, large, vector, prediction] [factor, local, structure, update, computation] [covariance, updating, true, stochastic, matrix, proposed, order, analysis] [posterior, time, multivariate, model, lbcr, series, locally, bayesian, conditional, latent, figure, simulation, crisis, process, gaussian, continuous, gibbs, smoothing, distribution, prior, nonparametric, log, bcr, usa, data, nasdaq, dunson, journal, dependence, predictive, national, rapid, nsi, wishart, observed] [smoothness, regression, set, formulation, consider, shrinkage, selection] [varying, dynamic, simple, sharp, simulated, ahead]
Optimistic Concurrency Control for Distributed Unsupervised Learning
Xinghao Pan, Joseph E. Gonzalez, Stefanie Jegelka, Tamara Broderick, Michael Jordan
Xinghao Pan, Joseph E. Gonzalez, Stefanie Jegelka, Tamara Broderick, Michael Jordan
[algorithm, optimistic, conference, online, apply, state, inventory, execution] [learning, feature, international, work, large, preserving, unsupervised, approach, validation, second, based] [occ, distributed, cluster, serial, concurrency, ofl, accepted, scalability, parallel, facility, serially, clustering, global, runtime, scaling, size, serialization, existing, michael, product, operation, scalable, acm, communication, parallelism, supported, validated, serializable] [number, proposed, epoch, analysis, computing, additional] [data, processing, figure, process, generated, model, zik, probability, parameter, nonparametric, dirichlet, bayesian, perfect] [machine, set, approximation, point, cost, theoretical, easily, theorem, proof, database] [control, location, neural, pattern, strong, correct]
Auxiliary-variable Exact Hamiltonian Monte Carlo Samplers for Binary Distributions
Ari Pakman, Liam Paninski
Ari Pakman, Liam Paninski
[algorithm, initial, space, state, jump] [work, approach, momentum] [binary, variable, move, allows] [coordinate, method, faster, order, proposed, quadratic, rate, random, arxiv, preprint, sparse] [hmc, model, gaussian, sampler, distribution, sample, time, metropolis, chain, markov, continuous, gibbs, monte, hamiltonian, particle, wall, sampling, truncated, ising, exact, carlo, figure, bayesian, prior, illustrate, boundary, piecewise, travel, computational, posterior, log, inverse, hill, successive, exponential, slab, journal, continues, orthant, discrete, multivariate] [regression, linear, consider, energy, case, statistical, interested, cost, clearly, problem, lower, function, solution, probit] [motion, hit, trajectory, leave, periodic]
Adaptive Step-Size for Policy Gradient Methods
Matteo Pirotta, Marcello Restelli, Luca Bascetta
Matteo Pirotta, Marcello Restelli, Luca Bascetta
[policy, bound, step, state, itmax, reinforce, bounded, difference, upper, action, pgt, expected, optimal, reward, advantage, natural, assumption, future, discounted, maximized, converge, supremum, episodic, scenario, deterministic, choice] [performance, learning, large, vector, table, approach] [size, starting, allows, pair, improvement, search, larger] [gradient, variance, number, convergence, error, small, basis, direction, uniformly, order, divergence, proposed, lead, quadratic, stochastic, norm, updated] [gaussian, estimate, distribution, stationary, positive, exact, parameter, probability, model, processing, generated] [lower, approximation, theorem, corollary, lemma, problem, function, consider, derive, provide, approximated, polynomial, case, guaranteed, estimator] [estimated, neural, control, speed]
Probabilistic Principal Geodesic Analysis
Miaomiao Zhang, P.T. Fletcher
Miaomiao Zhang, P.T. Fletcher
[space, exp, initial, algorithm] [vector, unit, truth, work, computer] [probabilistic, variable, ground, factor, parallel] [principal, analysis, gradient, sphere, euclidean, random, symmetric, pca, standard, matrix, denotes, proposed, variation] [riemannian, data, geodesic, manifold, model, latent, exponential, estimation, component, log, pga, tangent, derivative, monte, carlo, jacobi, corpus, ppga, distribution, callosum, normal, figure, parameter, expectation, gaussian, sample, normalizing, bayesian, processing, include, hamiltonian, nonlinear, covariant, base, likelihood, geometry, kernel, respect, hmc] [map, point, linear, set, maximization, note, procedure, function, maximum, formulation, integral, constant, density, denote, kendall, geometric] [shape, complex, estimated, rotation, term, velocity, neural, simulated]
Mixed Optimization for Smooth Functions
Mehrdad Mahdavi, Lijun Zhang, Rong Jin
Mehrdad Mahdavi, Lijun Zhang, Rong Jin
[algorithm, optimal, goal, assume, assumption, bound, making, setting, online, sequence, fact, sampled, step, deterministic, regret] [domain, improve, based, achieve, training, learning, average, approach, improved, amount, introduced, better] [mixed, size, compute, distributed, allows] [stochastic, gradient, optimization, convergence, rate, oracle, convex, number, objective, method, descent, small, kth, epoch, proposed, mixedgrad, optimizing, regularization, order, key, norm, sgd, variance, stochastically, accelerated, rgit, computing, call] [full, probability, parameter, journal, sample] [function, smooth, solution, loss, theorem, proof, smoothness, access, lemma, machine, main, problem, min, note, result, constant, cost, minimizes, set, consider, example, lipschitz] [strong]
Projecting Ising Model Parameters for Fast Mixing
Justin Domke, Xianghang Liu
Justin Domke, Xianghang Liu
[algorithm, total, bound, projected, converge] [original, based, accuracy, work, well] [strength, inference, edge, graph, tree, projecting, loopy, mixed, size] [divergence, euclidean, fast, norm, spectral, random, projection, matrix, gradient, number, singular, distance, computing, stochastic, method, descent] [gibbs, mixing, sampling, piecewise, ising, interaction, distribution, marginals, approximate, exact, time, markov, tractable, model, chain, exponential, parameter, lbp, respect, dependency, family, sample, estimate, rapid, stationary, probability, variational, intractable, accurate, univariate] [set, trw, consider, case, theorem, result, simply, general, density, guaranteed, approximation, guarantee, arg] [attractive, estimated]
Which Space Partitioning Tree to Use for Search?
Parikshit Ram, Alexander Gray
Parikshit Ram, Alexander Gray
[algorithm, bounded, best, conference, space, bound, chosen, worst, assumption, expected] [performance, margin, large, better, vector, based, dataset, improved, task, learning] [search, tree, quantization, depth, partition, neighbor, candidate, node, split, size, alternate, improvement, hyperplane, binary, nearest, smaller, traversal, clustering, explicitly, disjoint, corresponds, defeatist, balance] [error, distance, expansion, covariance, rank, hash, number, convex, hashing, dimensionality, imply, rate, random, principal, high, matrix] [data, partitioning, axis] [implies, set, theoretical, query, condition, result, theorem, constant, guarantee, consider, case, corollary] [region, balanced, ieee, depends]
Conditional Random Fields via Univariate Exponential Families
Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Zhandong Liu
Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Zhandong Liu
[] [learning, class, vector, learn, well, feature, based, common, computer, compared] [graph, graphical, structure, neighborhood, compatibility, size, node, undirected, corresponds, allows] [random, method, recovery, analysis, rate, arxiv, key, preprint, sparsity, sparse, regularization] [conditional, crf, distribution, exponential, gaussian, model, crfs, covariates, family, univariate, joint, data, form, poisson, ising, conditioned, multivariate, positive, observation, gene, parameter, three, figure, estimation, glioblastoma, rest, including] [set, theorem, covariate, consider, function, statistical, selection, suppose, provide, linear, distributional, general, framework, note, mrf, question, depend, consistent] [response, false, novel, corresponding]
Provable Subspace Clustering: When LRR meets SSC
Yu-Xiang Wang, Huan Xu, Chenlei Leng
Yu-Xiang Wang, Huan Xu, Chenlei Leng
[conference, deterministic, space, algorithm, assume, difference, absolute, assumption] [computer, international, representation, segmentation, unit, better, vision, learning, vector, large] [clustering, graph, disjoint, represents, connected] [subspace, matrix, spectral, ssc, sep, sparse, lrssc, singular, dual, norm, lrr, random, gap, analysis, incoherence, noisy, skewed, numerical, convex, remark, nuclear, inradius, block, robust, relviolation, sparsity, imply, sphere, diagonal, exactly] [data, log, figure, model, sample, probability, generated, distribution, parameter, illustrate] [solution, problem, condition, lemma, min, machine, theorem, example, set, constant, ratio, theoretical, selection, guarantee, studied, proof, main, linear, version] [connectivity, pattern, ieee, range, normalized, greater, correct, motion]
Stochastic blockmodel approximation of a graphon: Theory and consistent estimation
Edoardo M. Airoldi, Thiago B. Costa, Stanley H. Chan
Edoardo M. Airoldi, Thiago B. Costa, Stanley H. Chan
[algorithm, sequence, bound, step, expected, goal, optimal] [experiment, better, evaluate, large, second, performance, based, learning, similarity] [graph, missing, network, blockmodel, assign, size, vertex, mae, relational] [graphon, proposed, stochastic, number, usvt, bbi, random, block, dij, graphons, bdij, error, growing, matrix, bbk, bbj, row, method, distance, analysis, small] [sba, estimate, estimation, observed, figure, journal, exchangeable, probability, generated, independent, latent, data, parameter, nonparametric, ujv, continuous, piecewise, bayesian, model] [theorem, lemma, function, estimating, consider, consistency, estimator, procedure, idea, approximation, machine, theory, constant, empirical, consistent, statistical] [estimated]
Generalized Random Utility Models with Multiple Types
Hossein Azari Soufiani, Hansheng Diao, Zhenyu Lai, David C. Parkes
Hossein Azari Soufiani, Hansheng Diao, Zhenyu Lai, David C. Parkes
[agent, utility, algorithm, chosen, partial, choice, jump] [type, multiple, work, performance, based, propose, approach] [clustering, synthetic, real, inference, james, move, david] [number, random, matrix, method, order, true, proposed] [data, model, alternative, prior, posterior, journal, likelihood, log, interaction, grums, economics, figure, university, steven, estimate, mixture, observed, equal, estimation, economic, daniel, reversible, sample, consumer, parameter, probability, harvard, logit] [set, function, case, ranking, sushi, generalized, concave, theorem, grum, consider, proof, establish, provide, rjmcmc, suppose, theory, azari, select, theoretical, statistical, result] [involving, preference, unobserved, study, consisting, intrinsic]
Bayesian Hierarchical Community Discovery
Charles Blundell, Yee Whye Teh
Charles Blundell, Yee Whye Teh
[greedy, algorithm, worst, current] [hierarchical, work, hierarchy, better, large, top, propose, score, approach, learning, scale] [tree, bhcd, community, structure, network, social, adjacency, relational, inference, whilst, irm, binary, edge, forest, partition, merge, cluster, discovering, blockmodel, monastery, pair, merges, computed, formed, root, factor, local, corresponds, rose] [number, stochastic, sparse, block, iteration, matrix, faster, method] [model, bayesian, figure, likelihood, data, time, probability, prior, predictive, marginal, nonparametric, log, latent, computational, full, observed, describe] [complexity, yield, case, procedure, consistent] [potential, inferring, single, connectivity, neural]
Optimistic policy iteration and natural actor-critic: A unifying view and a non-optimality result
Paul Wagner
Paul Wagner
[policy, optimistic, natural, greedy, step, optimal, oscillation, reinforcement, methodology, vanishingly, established, special, interpolation, algorithm, action, origin, limiting, converge, markovian, conference, deterministic, current, programming, state, bounded, decision, focus, difference, permit] [learning, evaluation, temperature, class, vector, approach, well, international] [size, improvement, factor, understanding] [convergence, gradient, stochastic, iteration, uniformly, distance, small, practical, direction, lead, sustained] [parameter, approximate, gibbs, form, figure, process, extended, journal, monte, markov, carlo] [function, case, optimum, point, theorem, result, problem, effective, close, optimality, consider, machine, subset, general, version, map] [dynamic, term, neural, assuming, behavior]
Predictive PAC Learning and Process Decompositions
Cosma Shalizi, Aryeh Kontorovitch
Cosma Shalizi, Aryeh Kontorovitch
[algorithm, bound] [image, based, large, work, better] [local, degree, structure, existing, associated] [sparse, additional, column, exactly, unknown, analysis, proposed, variance, comparison, operator, true, norm, homotopy, optimization, sparsity, projection, typically] [log, model, kernel, estimation, figure, form, process, element, bayesian, likelihood] [function, penalty, cost, concave, min, note, selection, simply, general, theoretical, result, regression, paper] [blur, deblurring, blind, camera, blurry, sharp, noise, estimated, uniform, shake, motion, relative, greater, deconvolution, concavity, normalization, single, simple, continuation, meaning, gupta, reparameterization, hirsch, blurring, undesirable, viewed, harmeling, joshi, corresponding, whyte]
From Bandits to Experts: A Tale of Domination and Independence
Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour
Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour
[regret, bound, action, observability, setting, algorithm, dominating, bandit, upper, uninformed, player, expert, reveals, adversarial, called, partial, optimal, variant, logarithmic, playing, observe, learner, greedy, online, quantity, elp, sequence, step, current, observes] [prediction, learning, knowledge] [graph, directed, undirected, informed, acyclic, size, edge, compute, social] [number, symmetric, analysis, standard, order, random, key, minimum, grant] [observation, independence, time, independent, model, prior, distribution, generated, probability] [set, corollary, loss, lower, case, max, consider, arc, result, problem, cover, subset, linear, note, theorem, general, program, studied, israel, example] [system, simple, corresponding]
Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization
Nataliya Shapovalova, Michalis Raptis, Leonid Sigal, Greg Mori
Nataliya Shapovalova, Michalis Raptis, Leonid Sigal, Greg Mori
[action, algorithm, space, actor, focus] [video, localization, context, bounding, learning, bow, recognition, discriminative, box, training, feature, table, prediction, visual, representation, detection, average, output, multiple, based, score, approach, scoring, truth, object, weak, localize, performance, test, svm, amount, propose, evaluation, incorporating, ability, well, evaluate, excluding, dataset] [search, local, global, allows, person, path, ground, inference] [proposed] [latent, model, data, background, form] [function, structured, density, loss, map, linear, smooth, formulation, set, case] [gaze, saliency, region, human, eye, salient, inferred, temporal, frame, response, capture, interest, spatial, tran, perceptually, motion, potential, overlap]
Efficient Optimization for Sparse Gaussian Process Regression
Yanshuai Cao, Marcus A. Brubaker, David Fleet, Aaron Hertzmann
Yanshuai Cao, Marcus A. Brubaker, David Fleet, Aaron Hertzmann
[algorithm, free, greedy, space, total] [training, input, test, performance, learning, vector, better, good, dataset, hyperparameter, evaluating, negative, large, based, compare, hog, domain, evaluation] [update, candidate, optimizes] [objective, optimization, sparse, factorization, random, matrix, number, covariance, swap, method, variance, small, titsias, rank] [inducing, discrete, continuous, time, gaussian, kernel, variational, process, log, approximate, spgp, cholesky, exact, likelihood, smse, data, full, hyperparameters, ivm, residual, cholqr, figure, csi, predictive, snlp, form, swapping, marginal, element] [set, point, select, approximation, selection, function, regression, cost, energy, lower, machine, complexity, subset] [change, single]
Aggregating Optimistic Planning Trees for Solving Markov Decision Processes
Gunnar Kedenburg, Raphael Fonteneau, Remi Munos
Gunnar Kedenburg, Raphael Fonteneau, Remi Munos
[optimal, algorithm, space, simplex, fact, sum] [metric, well, vector, mnist, large, negative, original, better, propose, image] [scaling, computed, network, computation, perform, compute] [transport, distance, matrix, pij, sinkhorn, qjk, number, divergence, classic, emd, computing, regularization, gpu, earth, euclidean, entropic, iteration, mij, regularized, rct, convergence, random, small, cpu, argmin] [entropy, joint, figure, kernel, probability, computational, log, independence, positive, equation, form, mutual, time, journal, family] [problem, set, point, cost, proof, lemma, theory, consider, linear, theorem, dimension, prove, provide, inequality, subset, extreme] [single, varying, property, speed]
Learning the Local Statistics of Optical Flow
Dan Rosenbaum, Daniel Zoran, Yair Weiss
Dan Rosenbaum, Daniel Zoran, Yair Weiss
[natural, algorithm, availability, black] [computer, learned, image, better, truth, vision, learn, patch, large, compare, training, performance, test, hidden, international, amount, work, outperforms, learning, dataset, vector, second] [local, ground, inference, conditioning, michael, improvement] [matrix, robust, eigenvectors, standard, subspace, covariance, comparing, success, row, small, expect, leading, optimization] [optical, intensity, model, gaussian, prior, likelihood, log, data, figure, estimation, kitti, component, held, mixture, boundary, sintel, generated, allow, multidimensional, transition, modeling, conditioned, conditional, restoration, markov] [gmm, smoothness, set, suggested, linear, function, constant] [motion, horn, term, noise, pattern]
Estimation Bias in Multi-Armed Bandit Algorithms for Search Advertising
Min Xu, Tao Qin, Tie-Yan Liu
Min Xu, Tao Qin, Tie-Yan Liu
[revenue, adaptive, mab, algorithm, advertiser, utility, incentive, ucb, expected, ctr, auction, payment, history, best, engine, debiasing, bound, assume, elm, bid, unif, impression, adpt, regret, satisfy, fact, gain, charge, advertising, price, slot, bandit, game, display, setting, maxk, sponsored] [learning, second, quality, vector, negative, work, propose, large] [search, larger, stage, smaller, compatibility, concentration] [number, largest, low, analysis, order, high, random] [log, sample, probability, estimation, figure, estimate, measure] [selection, bias, min, theorem, loss, suppose, estimator, analyze, select, arg, case, guarantee, corollary, lower, condition, example, unbiased, theoretic] [click, uniform, simple, increase, described]
Robust learning of low-dimensional dynamics from large neural ensembles
David Pfau, Eftychios A. Pnevmatikakis, Liam Paninski
David Pfau, Eftychios A. Pnevmatikakis, Liam Paninski
[natural, space, history, state, optimal] [directly, learning, large, top, common, vector, prediction, direct, approach] [real, local, global] [norm, nuclear, matrix, subspace, true, principal, explained, recovered, method, divergence, number, bregman, variance, convex, recover, analysis, rate, dimensionality, spectral, singular, dimensional, rank, spanned, sparse, low, ssid] [data, model, log, latent, likelihood, component, journal, time, held, gaussian, transition, process, poisson, observed, processing, include, figure, parameter] [linear, case, minimization, penalty, statistical, generalized, point, dimension, function, paper] [neural, spike, dynamical, synaptic, system, connectivity, population, term, angle, motor, stable, presented, strong, account]
On model selection consistency of penalized M-estimators: a geometric theory
Jason Lee, Yuekai Sun, Jonathan E. Taylor
Jason Lee, Yuekai Sun, Jonathan E. Taylor
[assumption, sum, state, optimal, assume] [work, learning, large, vector] [group, graphical, neighborhood, size, van, supported, science] [norm, convex, subspace, minimize, unknown, sparsity, covariance, sparse, supplementary, error, dual, analysis, high] [model, exponential, likelihood, estimation, log, sample, parameter, probability, family, inducing, estimate] [consistency, lasso, selection, decomposable, geometrically, generalized, penalty, support, penalized, function, notion, result, maximum, main, framework, irrepresentable, hdt, condition, solution, linear, expressed, negahban, statistical, set, theorem, estimator, general, inf, select, derive, suppose, problem, establishing, consistent, constant, regression, loss, engineering, consider, generalize, corollary, commonly, convexity, establish] [strong, signal, enforce]
New Subsampling Algorithms for Fast Least Squares Regression
Paramveer Dhillon, Yichao Lu, Dean P. Foster, Lyle Ungar
Paramveer Dhillon, Yichao Lu, Dean P. Foster, Lyle Ungar
[algorithm, setting, bound, assume, failure, best, long] [vector, datasets, work, amount, well, second, approach, large, compare, better, performance, accuracy] [randomized, synthetic, real, stage, subsample] [error, random, matrix, subsampling, hadamard, uluru, covariance, nsubs, transform, covs, preconditioning, subsampled, analysis, ols, number, fast, yrem, leverage, high, supplementary, corr, faster, uniformly, small, srht, fraction, remark, fourier, noisy, performs, standard, wcorrect] [data, three, probability, estimate, time, independent, full, estimation, parameter, figure] [design, theoretical, theorem, paper, linear, case, provide, estimator, set, problem, loss, estimating, squared, regression, consider, result] [described, noise, depends, varying, material, term]
Dropout Training as Adaptive Regularization
Stefan Wager, Sida Wang, Percy Liang
Stefan Wager, Sida Wang, Percy Liang
[adaptive, natural, online, conference, apply, linearized] [dropout, training, feature, noising, unlabeled, learning, rare, accuracy, vector, labeled, table, def, test, dataset, fisher, discriminative, level, large, imdb, based, international, noised, better, performance, well, applied, train, sida, generative, text, christopher] [size, applying] [quadratic, regularization, adagrad, matrix, sgd, descent, stochastic, random, small, method, solving, ridge] [data, form, additive, estimate, model, figure, computational, parameter, processing, simulation, gaussian, document, independent, journal] [penalty, logistic, regression, linear, approximation, regularizer, equivalent, loss, machine, design, problem, case, depend, active, empirical, function, consider] [noise, neural, connection]
Using multiple samples to learn mixture models
Jason Lee, Ran Gilad-Bachrach, Rich Caruana
Jason Lee, Ran Gilad-Bachrach, Rich Caruana
[algorithm, space, assume, maximal, return, assumption, goal, maintain, projected] [learning, multiple, work, applied, large, second, appear, experiment, hidden, computer, compare] [msp, dsc, tree, clustering, underlying, disjoint, cluster, symposium, annual, leaf, associated, vempala] [projection, variance, dimensional, low, random, project, spanned, distance, require, method, high, analysis, error, spectral] [mixture, sample, data, gaussians, mixing, figure, model, probability, generated, three, log, assumes, measure, address, usa, topic] [problem, dimension, separation, case, result, set, exists, polynomial, theorem, santosh, complexity, main] [presented, single, blue, noise, ieee]
Annealing between distributions by averaging moments
Roger B. Grosse, Chris J. Maddison, Ruslan Salakhutdinov
Roger B. Grosse, Chris J. Maddison, Ruslan Salakhutdinov
[optimal, initial, linearly, natural] [target, hidden, rbms, learning, deep, visible, based, performance, boltzmann, rbm, mnist, table, training, average] [path, partition] [averaging, analysis, rate, high, order, number, proposed, variance] [log, intermediate, moment, sampling, exponential, perfect, intractable, schedule, family, figure, distribution, probability, model, tractable, sample, base, binned, gibbs, accurate, annealed, variational, annealing, restricted, spaced, alternative, monte, exact, markov, derived, estimate, transition, interpolate, piecewise] [geometric, linear, theorem, cost, function, set, result, estimating, machine, asymptotically, consider, statistical] [uniform, functional, viewed, indicate]
Learning Hidden Markov Models from Non-sequence Data via Tensor Decomposition
Tzu-Kuo Huang, Jeff Schneider
Tzu-Kuo Huang, Jeff Schneider
[state, initial, algorithm, formal, setting, appendix, sequence, expected, assume, sequential, easier] [learning, hidden, generative, multiple, based, input, large, consistently, learn] [size, structure, network] [tensor, matrix, decomposition, method, spectral, true, unknown, random, recover, order, column, small, projection, number, array, usual, arxiv] [data, markov, distribution, sample, transition, model, estimation, process, probability, estimate, latent, figure, issue, dirichlet, modeling, independent, draw, chain, topic, three, generated, observation, time, returned, discrete, observed, hmm] [set, empirical, theorem, theoretical, consistent, complexity, note, problem, proof, guarantee, result, general, procedure] [dynamic, biological, situation]
Accelerated Mini-Batch Stochastic Dual Coordinate Ascent
Shai Shalev-Shwartz, Tong Zhang
Shai Shalev-Shwartz, Tong Zhang
[algorithm, bound, deterministic, peter, assume, choose] [learning, better, training, table, vector, opening, nesterov, dataset, compare] [parallel, node, distributed, communication, size, martin, joseph, processed, message, runtime] [sdca, asdca, dual, iteration, gradient, agd, descent, stochastic, coordinate, accelerated, number, arxiv, preprint, computing, zhang, method, interpolates, convex, examplestest, rate, sgd, ascent, regularization, euclidean, analysis, mentioned, convergence, optimization, norm, dividing, solving, alekh, carlos] [time, data, processing] [cost, loss, machine, studied, consider, primal, shai, case, main, function, smooth, problem, version, complexity, paper, set, tong, solution, hold, example, max, subset] [single]
Faster Ridge Regression via the Subsampled Randomized Hadamard Transform
Yichao Lu, Paramveer Dhillon, Dean P. Foster, Lyle Ungar
Yichao Lu, Paramveer Dhillon, Dean P. Foster, Lyle Ungar
[algorithm, space, setting, step] [large, vector, better, compare, well, feature, training, randomly, approach, dataset, setup, weight, top] [randomized, compute, median, computed, synthetic, real, size, parallel, structure, michael] [matrix, pca, psubs, true, ridge, random, dual, error, hadamard, transform, fast, computing, standard, srht, subsampled, rate, number, rank, analysis, high, principal, faster, svd, subsampling, huge, low, solutionpcarandomized, remark, ordinary, multiplication, solving] [computational, data, kernel, generated, figure, probability, power, time, equation, parameter, approximate] [risk, regression, cost, design, solution, pcr, approximation, linear, lemma, case, dimension, problem, provide, paper, statistical] [slow, mark]
Recurrent linear models of simultaneously-recorded neural populations
Marius Pachitariu, Biljana Petreska, Maneesh Sahani
Marius Pachitariu, Biljana Petreska, Maneesh Sahani
[state, best, upper, deterministic] [output, better, performance, large, prediction, approach, well, hidden, directly, generative, common] [structure, factor, link, inference] [matrix, covariance, number, random, subspace, gradient, standard, pairwise, principal] [model, rlm, data, latent, lds, gaussian, distribution, poisson, ising, cglm, time, likelihood, equation, observation, describe, figure, process, replacing, estimate, three, computational, psth, alternative, conditional, instantaneous, cascaded, form, generated, plds, nonlinear] [linear, case, function, provide, note, consider] [neural, spike, dynamical, kalman, population, recurrent, simulated, recorded, temporal, estimated, noise, activity, generalisation, simple, neuronal, glm, motor]
Learning Adaptive Value of Information for Structured Prediction
David J. Weiss, Ben Taskar
David J. Weiss, Ben Taskar
[policy, state, reward, action, optimal, expected, current, space, adaptive, setting, total, reinforcement, choosing, future, add, sequence, goal, ocr] [feature, learning, learn, extraction, approach, prediction, vector, pose, work, training, extracted, accuracy, input, output, large, learned, based, test, level, video, achieve] [inference, compute, computed, computation, structure, runtime, graph] [error, method, additional, standard, rate, proposed, computing, typically] [model, time, accurate, approximate, figure, predictive, computational, markov, component, allow] [budget, structured, set, function, cost, note, simply, example, problem, effective, batch, predictor, consider, linear, selection, indicator] [control, frame, simple, trajectory, human, imitation, increase]
When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
Anima Anandkumar, Daniel Hsu, Majid Janzamin, Sham M. Kakade
Anima Anandkumar, Daniel Hsu, Majid Janzamin, Sham M. Kakade
[denoted, long, deterministic, bound, space] [hidden, class, award, vector, word, learning, generic, representation] [structure, graph, size, degree, variable, product, node] [overcomplete, random, order, matrix, matching, number, tensor, rank, persistence, sparsity, remark, expansion, uniqueness, tucker, krank, generically, recovery, incorporate, analysis, column, persistent, canonical, discussion, existence, imply, characterize] [topic, model, observed, moment, latent, admixture, perfect, log, full, figure, distribution, referred, probability, form, equation, university, aro, drawn] [condition, bipartite, theorem, establish, set, result, version, structured, general, note, consider, provide, case] [population, higher, single, novel, constraint, presence, pattern]
Estimating LASSO Risk and Noise Level
Mohsen Bayati, Murat A. Erdogdu, Andrea Montanari
Mohsen Bayati, Murat A. Erdogdu, Andrea Montanari
[sequence, state, algorithm, lim] [level, vector, well] [evolution, applying, scaled, versus, represents, message, passing, color] [method, amp, error, standard, variance, matrix, regularization, true, random, order, iteration, compressed, remark, accurately, dimensional, basis, covariance, numerical, analysis] [gaussian, distribution, asymptotic, estimation, model, iid, estimate, inverse, figure, parameter, probability, generated, multivariate, independent, data, normal] [lasso, estimator, design, theorem, risk, general, unbiased, converging, denote, provide, squared, conjecture, corollary, consistent, statistical, problem, function, mse, linear, converges, result, empirical, weakly, estimating, main, note, consistency, annals, case, solution, suitable, formula, support, selection, msetrue, point] [noise, signal, estimated, ieee]
Relevance Topic Model for Unstructured Social Group Activity Recognition
Fang Zhao, Yongzhen Huang, Liang Wang, Tieniu Tan
Fang Zhao, Yongzhen Huang, Liang Wang, Tieniu Tan
[bound, action] [video, rtm, learning, relevance, replicated, training, vector, softmax, supervised, unstructured, dataset, semantic, accuracy, learn, bow, labeled, discriminative, work, better, hidden, boltzmann, wedding, recognition, svm, medlda, learned, jointly, visible, unit, class, automatic, table, gclass, discover, med, word] [social, undirected, multimodal, inference, group, graphical, binary, directed, web] [sparse, number, small, proposed, stochastic] [model, topic, variational, log, data, latent, distribution, bayesian, figure, likelihood, marginal, parameter, restricted, estimation, lda, gaussian, posterior, estimate, equation, three, conditional, wijvmi, contrastive] [function, linear, set, case, lower, maximum] [activity, complex, attribute, human, calculate]
Context-sensitive active sensing in humans
Sheeraz Ahmad, He Huang, Angela J. Yu
Sheeraz Ahmad, He Huang, Angela J. Yu
[belief, optimal, policy, action, switching, state, bound, strategy, decision, making, space, future, expected, assume, choice, choose, current, total, sequential, step] [target, visual, patch, better, task, performance, based, well, unit, compare, accuracy, context, work] [search, optimize] [number, proposed, block] [time, data, prior, model, probability, boundary, figure, bayesian, distribution, likelihood, sampling, processing] [cost, active, min, set, bias, function, case, approximation, theorem] [location, sensing, myopic, infomax, human, stopping, behavioral, control, behavior, dynamic, threshold, observer, presented, eye, brain, sensory, incurred, account, declare, experimental, simple, novel, trial, neural, spatial]
Confidence Intervals and Hypothesis Testing for High-Dimensional Statistical Models
Adel Javanmard, Andrea Montanari
Adel Javanmard, Andrea Montanari
[optimal, assume, bound, minimax, assumption, notice] [vector, test, approach, level, constructing, work] [size, construct, compatibility, binary, variable, van] [matrix, random, standard, covariance, sparse, regularized, error, order, method, dimensional, sparsity, convex, norm, high, denotes, number, variance] [testing, log, parameter, probability, gaussian, power, sample, model, estimate, asymptotic, distribution, estimation, normal, plot, exact, observed] [statistical, design, linear, hypothesis, estimator, regression, theorem, set, lasso, consider, procedure, condition, support, general, javanmard, selection, logistic, interval, consistent, provide, min, note, asymptotically, diabetes, letting, quantiles, classical, construction] [response, simple, normalized, earlier, ieee, term, corresponding, noise]
Factorized Asymptotic Bayesian Inference for Latent Feature Models
Kohei Hayashi, Ryohei Fujimaki
Kohei Hayashi, Ryohei Fujimaki
[algorithm, bound, satisfy, natural, acceleration, fact, elapsed, setting] [learning, feature, performance, large, achieved, representation, better, hidden, automatic] [inference, update, smaller, irrelevant, variable, real, unique] [method, analysis, matrix, regularization, number, supplementary, hessian, block, gradient, standard, empirically, convex, faster] [fab, log, latent, model, computational, fic, meibp, ibp, respect, bayesian, lfms, asymptotic, data, parameter, marginal, time, figure, znk, variational, factorized, indian, buffet, cccp, observed, form, distribution, sample, nonparametric, ficmm, yaleb, sampling, prior, shrinking, fics] [lower, approximation, shrinkage, selection, condition, set, note, lemma, case, machine, complexity, equivalent, theorem, asymptotically, deviation] [term, neural, increase, noise]
Tracking Time-varying Graphical Structure
Erich Kummerfeld, David Danks
Erich Kummerfeld, David Danks
[algorithm, online, current, assume, sequence, expected, previous] [learning, performance, learn, large, based, tracking, weight, multiple, shift, work, predict] [structure, losst, graphical, graph, relearning, size, datapoint, mahalanobis, datapoints, underlying, edge, weighted, pooled, changed, update, provably, respond, convergent, sem, perform, heuristic, undirected, focused, mellon, occurred, occur, recursive] [number, standard, distance, covariance, convergence, matrix, method] [model, data, sample, generating, bayesian, probability, locally, time, equation, figure, parameter, track, university, detect, stationary, generated, full] [effective, set, cost, provide] [change, stable, estimated, indicate]
Compressive Feature Learning
Hristo S. Paskov, Robert West, John C. Mitchell, Trevor Hastie
Hristo S. Paskov, Robert West, John C. Mitchell, Trevor Hastie
[algorithm, chosen, space, impact, best, sequence] [feature, compression, training, text, pointer, dictionary, learning, class, unsupervised, newsgroups, work, representation, word, task, accuracy, good, performance, based, computer, well, categorization, datasets, large, appear, description, reweighting, extract, approach, imdb, separately, demonstrate] [binary, structure, size, allows, split, stanford] [compressed, method, optimization, order, scheme, error, solve, regularization, minimize, small, solving, require, principal, admm, minimum, matrix, number, principle, dual, analysis] [data, document, testing, full, corpus, time, length, university, figure] [set, cost, problem, selection, solution, linear, machine, minimizing, criterion, reduces] [constraint, department, subject, single, storage]
Moment-based Uniform Deviation Bounds for $k$-means and Friends
Matus Telgarsky, Sanjoy Dasgupta
Matus Telgarsky, Sanjoy Dasgupta
[bound, bounded, appendix, upper] [work, scale, large, technique, class, applied, well] [size, clustering, source, allows, center, pair, cluster] [convex, norm, bregman, convergence, covariance, rate, divergence, standard, variance, soft] [sample, gaussian, probability, measure, likelihood, moment, distribution, mixture, draw, parameter, process, respect] [set, cost, outer, function, proof, condition, bracketing, bracket, theorem, empirical, consistency, consider, provide, note, lemma, lower, density, hard, case, suppose, maximum, deviation, corollary, consideration, stability, pollard, radius, simply, clamping, compact, technical, boundedness, ball, clamp, theory, point, beating, shamir] [corresponding, single, control, uniform, term]
Fast Template Evaluation with Vector Quantization
Mohammad Amin Sadeghi, David Forsyth
Mohammad Amin Sadeghi, David Forsyth
[conference, algorithm, current] [vector, detection, template, hog, object, score, computer, image, feature, evaluation, deformable, table, original, lookup, average, exemplar, vision, quantized, voc, evaluate, training, svm, convolution, work, compare, category, felzenszwalb, accuracy, evaluating, library, technique, multiple, approach, trained, top, detector] [quantization, cascade, computation, nearest] [method, number, fast, running, implementation, sparse, magnitude, speedup, precision, analysis, computing, faster, require] [time, process, dpm, estimate, sample, figure, estimation, model, major, approximate] [approximation, loss, linear, set, cost, version, machine, paper] [speed, pattern, ieee, cell, pascal, location]
k-Prototype Learning for 3D Rigid Structures
Hu Ding, Ronald Berezney, Jinhui Xu
Hu Ding, Ronald Berezney, Jinhui Xu
[algorithm, total, space, called, optimal] [learning, metric, average, weight, based, input, randomly, approach, transformation, quality, object, computer, evaluate, image] [clustering, graph, median, structure, compute, partition, build, determine, edge, reduce, triangle, existing, generate, smaller] [objective, matching, distance, minimum, random, euclidean, minimize, practical, pij, number, optimization, method] [data, approximate, figure] [problem, cost, point, set, bipartite, approximation, theorem, solution, consider, main, lemma, geometric, ratio, inequality, idea, constant, select, theoretical] [rigid, prototype, alignment, chromatic, chromosome, correlation, pattern, biological, cell, corresponding, sin, ieee, rotation, viewed, match, shape, presented, ding]
Variational Policy Search via Trajectory Optimization
Sergey Levine, Vladlen Koltun
Sergey Levine, Vladlen Koltun
[policy, ddp, algorithm, current, initial, gps, previous, exploration, optimal, variant, state, conference, guided, dagger, bound, deterministic, swimmer, walker, programming, reinforcement, locomotion, successful, adaptive, future, fxt] [learning, work, good, average, hidden, learned, international, learn, performed, approach, evaluation, improve, discover] [search, optimize, local, inference] [optimization, method, standard, objective, random, divergence, stochastic, low, magnitude, iterative, minimum, order, iteration] [log, variational, gaussian, distribution, likelihood, prior, nonlinear, respect, equation, optimized, marginals, sample, probability, drawn, sampling, entropy] [cost, maximum, solution, function, linear, machine, case, maximization, differential, approximation, example, effective] [trajectory, dynamic, control, complex, noise, neural, desired, highly, system]
A simple example of Dirichlet process mixture inconsistency for the number of components
Jeffrey W. Miller, Matthew T. Harrison
Jeffrey W. Miller, Matthew T. Harrison
[exp, step, fact, converge, focus, sum, apply, natural] [hierarchical, large, applied, unit, common, approach] [law, mass, clustering, extra, factor, concentration, illustrates, cluster] [number, standard, true, unknown, small, practical, heterogeneity, discussion] [dpm, normal, posterior, bayesian, process, mixture, data, dirichlet, model, distribution, prior, probability, inconsistency, component, equation, observed, dpms, log, marginal, nonparametric, concentrate, univariate, draw, parameter, university, measure, estimate, equal, journal, mixing, miller, family, figure, issue] [density, example, note, case, denote, proof, consistent, converges, set, tiny, general, function, consider, straightforward, prove, theoretical] [simple, strong, institute]
Training and Analysing Deep Recurrent Neural Networks
Michiel Hermans, Benjamin Schrauwen
Michiel Hermans, Benjamin Schrauwen
[long, state, conference, previous, sampled] [layer, output, text, training, top, deep, common, test, drnns, input, closing, trained, rnn, bottom, contribution, bpc, hidden, learning, context, character, hierarchy, performance, parenthesis, rnns, performed, drnn, architecture, language, opening, perturbed, hierarchical, typo, train, phrase, softmax, average, international, essentially, second, task, trainable, table, level, large, prediction] [network] [order, number, gradient] [time, figure, processing, full, data, three, probability, model, series, wikipedia, longer] [set, paper, machine, function, consider, provide, case, cost] [neural, recurrent, memory, temporal, individual, presented, single, study, increase, strong]
Scoring Workers in Crowdsourcing: How Many Control Questions are Enough?
Qiang Liu, Alex Ihler, Mark Steyvers
Qiang Liu, Alex Ihler, Mark Steyvers
[optimal, expected, assume, best, price, fewer, item, choice] [target, better, dataset, large, performance, datasets, randomly, accuracy, based, direct] [worker, real, assigned, assignment, graph, degree, regular] [number, random, true, matrix, unknown, xij, small] [model, joint, figure, data, log, asymptotic, estimate, gaussian, drawn, likelihood, processing, continuous, prior] [estimator, mse, consensus, budget, general, theoretical, provide, theorem, crowdsourcing, bipartite, set, bias, problem, nfl, note, denote, answer, estimating, point, crowdsourced, empirical, maximum, consider] [control, simple, estimated, simulated, varying, neural, closely, systematic, assuming]
Machine Teaching for Bayesian Learners in the Exponential Family
Xiaojin Zhu
Xiaojin Zhu
[learner, optimal, step, algorithm, space, fact, state, decision, setting, item, interesting, future, initial, choice, belief, making] [learning, target, training, good, concept, word, work, vector, second] [science] [optimization, minimum, number, convex, standard, error, discussed, small] [prior, log, bayesian, distribution, posterior, family, exponential, gaussian, model, form, figure, data, likelihood, iid, probability, conjugate, parameter, illustrate, three, multivariate, multinomial] [teaching, set, problem, aggregate, teacher, function, example, framework, effort, machine, cardinality, loss, unpacking, teach, note, case, dimension, label, unpack, solution, design, theory, mind, min, general, consider, consistent, active, complexity, easy, version] [cognitive, uniform, strong, threshold, corresponding, ten]
Robust Low Rank Kernel Embeddings of Multivariate Distributions
Le Song, Bo Dai
Le Song, Bo Dai
[algorithm, space, conference, appendix, bound, provided, step] [embedding, embeddings, feature, learning, second, hierarchical, vector, international, work, reshaping, truth, performance, view, datasets] [tree, variable, structure, product, compute, graphical, ground, edge, perform] [rank, low, decomposition, tensor, singular, order, spectral, reshape, matrix, dimensional, robust, operator, ordinary, number, caterpillar, error, frobenius, reshapings, basis, kde, norm, high, analysis, lead] [kernel, latent, data, conditional, model, intermediate, inner, hilbert, figure, observed, mixture, independence, joint, estimation, estimate, probability, gaussian] [density, empirical, set, machine, generalized, provide, denote, dimension, estimator, approximation, problem, lower, theoretical, point, theorem] [viewed, corresponding, term, higher]
Scalable kernels for graphs with continuous attributes
Aasa Feragen, Niklas Kasenburg, Jens Petersen, Marleen de Bruijne, Karsten Borgwardt
Aasa Feragen, Niklas Kasenburg, Jens Petersen, Marleen de Bruijne, Karsten Borgwardt
[algorithm, sum, total, advantage] [large, ith, table, datasets, vector, accuracy, based, learning, well, demonstrate, convolution, type, work, labeled] [node, graph, path, shortest, runtime, graphhopper, computation, tree, csm, edge, directed, synthetic, compute, diameter, dag, size, computed, airway, prop, appears, root, recursive, weighted, connected, source, real, rarely, classifying, kriege] [number, computing, hashing, random, comparing, matrix, small, high] [kernel, discrete, length, computational, log, figure, data, continuous, generated, time, university, dependence, asymptotic, parameter] [complexity, set, denote, machine, lemma, function, prove] [memory, attribute, simultaneously, sharing]
Graphical Models for Inference with Missing Data
Karthika Mohan, Judea Pearl, Jin Tian
Karthika Mohan, Judea Pearl, Jin Tian
[satisfy, called, outcome, complete, assumption] [dataset, report, work, representation, taxonomy, knowledge, computer] [missing, recoverability, missingness, recoverable, variable, graphical, mar, causal, partially, rvi, graph, relation, ordered, mcar, deletion, admissible, listwise, pam, imputation, depicted, treatment, compute, social, termed, mnar, recommender, applying, parent, deleted, los] [random, factorization, order, recovering, analysis, decomposition] [data, observed, figure, process, joint, distribution, estimate, sample, probability, conditional, latent, form, independent] [theorem, set, condition, example, mechanism, exists, problem, procedure, statistical, note, case, consistent, notion, lemma, general, corollary, minimal, strictly] [refer, estimated, corresponding, property]
The Randomized Dependence Coefficient
David Lopez-Paz, Philipp Hennig, Bernhard Schölkopf
David Lopez-Paz, Philipp Hennig, Bernhard Schölkopf
[space, choice, satisfy] [feature, table, large, vector, randomly, invariant, relationship, performance] [randomized, size, computation, variable, synthetic] [random, canonical, largest, number, projection, rank, distance, error, running, discussed] [dependence, rdc, sample, kernel, copula, distribution, marginal, figure, data, association, kcca, computational, chsic, hgr, hsic, log, measure, respect, independent, measuring, gaussian, multivariate, continuous, equal, power, dcor, additive, parameter, independence, probability, mic, bivariate, und, sampling] [set, linear, empirical, regression, theorem, estimator, cost, statistical, maximum, consider, selection, dom, function, annals, sinusoidal, fundamental, lemma, close, problem] [correlation]
Bayesian entropy estimation for binary spike train data using parametric prior knowledge
Evan W. Archer, Il M. Park, Jonathan Pillow
Evan W. Archer, Il M. Park, Jonathan Pillow
[space, choosing] [word, large, vector, excellent, illustrated, train, compare] [structure, binary, size, compute, concentration, real, computation, allows, distinct] [number, block, sparsity, small] [distribution, entropy, synchrony, prior, base, probability, dirichlet, mutual, model, measure, data, estimation, bayesian, time, bernoulli, estimate, sample, count, retinal, parametric, binomial, figure, observed, ganglion, nsb, discrete, bayes, drawn, posterior, iid, form, esd, dependence, ising, multinomial, parameter, centered] [empirical, estimator, estimating, problem, function, statistical, set, general] [spike, neural, population, correlation, simulated, capture, temporal, bin, single, study, spiking, uniform, highly, response]
Sign Cauchy Projections and Chi-Square Kernel
Ping Li, Gennady Samorodnitsk, John Hopcroft
Ping Li, Gennady Samorodnitsk, John Hopcroft
[bound, upper, projected, algorithm, apply, focus] [similarity, vector, computer, learning, second, based, propose, image, original, word, feature, better, training, validate, scale] [binary, search, solid, neighbor] [random, sign, tan, sparse, cauchy, method, ping, popular, proposed, libsvm, distance, acc, dashed, small, error, compressed, nonnegative, dept, fairly, streaming, computing] [data, probability, figure, kernel, generated, accurate, positive, nonlinear, exact, plot, length, model, processing, approximate] [approximation, linear, empirical, theoretical, machine, lemma, close, suitable, paper, function, tight] [collision, stable, study, stream, curve, simulated, sharp]
Approximate Dynamic Programming Finally Performs Well in the Game of Tetris
Victor Gabillon, Mohammad Ghavamzadeh, Bruno Scherrer
Victor Gabillon, Mohammad Ghavamzadeh, Bruno Scherrer
[policy, cbmpi, best, adp, game, space, rollout, dpi, board, algorithm, state, rollouts, height, bertsekas, greedy, controller, falling, action, programming, achieves, removed, regressor, piece, choice, fewer] [large, performance, score, reported, learning, evaluation, achieved, good, feature, based, learned, training, average, cross, literature, outperforms, table, applied, vector, direct] [search, size, compute, build] [iteration, number, small, method, error, averaged] [figure, parameter, approximate, sample, entropy, estimate, tion, markov, equation] [function, set, budget, approximation, note, empirical, select, linear, conjecture] [dynamic, study]
Extracting regions of interest from biological images with convolutional sparse block coding
Marius Pachitariu, Adam M. Packer, Noah Pettit, Henry Dalgleish, Michael Hausser, Maneesh Sahani
Marius Pachitariu, Adam M. Packer, Noah Pettit, Henry Dalgleish, Michael Hausser, Maneesh Sahani
[algorithm, natural, failure] [image, convolutional, learning, large, generative, pursuit, object, well, good, extracted, performance, activation, composed, approach, roc, segmentation, type, better, based, appear, consistently, learned, dictionary] [inference, tissue, real] [block, basis, number, small, matching, gradient, sparse, descent, true, recovers, incremental, recovered, principal, variance, noisy, svd, standard, order] [model, data, figure, full, prior, equation, parameter] [function, set, active, cost, note] [cell, biological, single, simulated, akl, spatial, coding, variability, false, calcium, repeating, human, imaging, location, cortical, positivestrue, typical, correct]
Multisensory Encoding, Decoding, and Identification
Aurel A. Lazar, Yevgeniy Slutskiy
Aurel A. Lazar, Yevgeniy Slutskiy
[current, space, natural, total, diagram] [video, audio, input, original, train, representation, multiple, visual, domain, performance, bandwidth, demonstrate] [multimodal] [number, projection, error, recovery, remark, matrix] [processing, kernel, time, three, generated, nonlinear, figure, reproducing, model] [linear, theorem, problem, rkhs, provide, set, dimension, interval, consider, note] [multisensory, neuron, spike, neural, population, sensory, encoding, uim, encoded, receptive, integration, hnm, circuit, temporal, xnm, aurel, iaf, single, phm, decoding, lnm, signal, produced, spiking, ideal, spatiotemporal, mtem, stimulus, brain, auditory, lazar, experimental, corresponding, tem, comprised, described, decoded, yevgeniy, response, dendritic]
Density estimation from unweighted k-nearest neighbor graphs: a roadmap
Ulrike Von Luxburg, Morteza Alamgir
Ulrike Von Luxburg, Morteza Alamgir
[step, difference, assume, conference] [learning, similarity, based, metric, embedding, large, second, unit, well, vector, international] [knn, path, graph, shortest, unweighted, underlying, directed, local, ordinal, leftd, neighbor, undirected, adjacency, logd, coincides, going, corresponds, anchor, von, hand, edge, vertex, compute] [distance, gradient, standard, true, order, small, sparse, matrix, number, recover, key, direction] [estimate, sample, log, data, figure, tangent, length, plot, multidimensional, continuous, distribution] [density, point, consider, proof, case, function, machine, problem, set, denote, integral, intuition, dimension, constant, proposition, argument, note, differentiable, general] [estimated, left, side, simple, uniform, integrating]
Decision Jungles: Compact and Rich Models for Classification
Jamie Shotton, Toby Sharp, Pushmeet Kohli, Sebastian Nowozin, John Winn, Antonio Criminisi
Jamie Shotton, Toby Sharp, Pushmeet Kohli, Sebastian Nowozin, John Winn, Antonio Criminisi
[decision, algorithm, optimal, current, total] [training, segmentation, learning, accuracy, test, generalization, compared, baseline, achieve, train, feature, image, work, large, jointly, randomly, class, report, level, prediction, conventional, better, propose, computer, improve, improved, dataset] [tree, node, split, dag, merged, merging, binary, rooted, child, leaf, priority, lsearch, parent, ensemble, jungle, reduce, size, datasetstandard, kinect, treesbaseline, scheduled, treesmerged, root, accuracytotal, forest, randomized, optimize, grass, structure] [number, standard, objective, method, optimizing, small, optimization] [model, data, figure] [set, machine, function, uci, note, minimization, maximum, compact, cost] [memory, reduced, ieee]
Non-Uniform Camera Shake Removal Using a Spatially-Adaptive Sparse Penalty
Haichao Zhang, David Wipf
Haichao Zhang, David Wipf
[algorithm, bound] [image, based, large, work, better] [local, degree, structure, existing, associated] [sparse, additional, column, exactly, unknown, analysis, proposed, variance, comparison, operator, true, norm, homotopy, optimization, sparsity, projection, typically] [log, model, kernel, estimation, figure, form, process, element, bayesian, likelihood] [function, penalty, cost, concave, min, note, selection, simply, general, theoretical, result, regression, paper] [blur, deblurring, blind, camera, blurry, sharp, noise, estimated, uniform, shake, motion, relative, greater, deconvolution, concavity, normalization, single, simple, continuation, meaning, gupta, reparameterization, hirsch, blurring, undesirable, viewed, harmeling, joshi, corresponding, whyte]
Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs
Yann Dauphin, Yoshua Bengio
Yann Dauphin, Yoshua Bengio
[algorithm, achieves, advantage, belief] [srm, training, rbms, input, learning, trained, rbm, deep, reconstruction, jrm, feature, test, based, table, good, propose, performance, boltzmann, train, better, hidden, sml, unsupervised, average, large, newsgroups, text, score, validation, mlp] [computation] [matching, number, stochastic, objective, sparse, error, scheme, variance, small, gradient, random, speedup, requires, stochastically] [sampling, distribution, biased, computational, restricted, model, data, proposal, estimation, form, time, equation, figure, estimate, probability, chain, monte, discrete, carlo, dauphin] [ratio, set, estimator, linear, machine, constant, unbiased, idea, subset, function, case] []
Discriminative Transfer Learning with Tree-based Priors
Nitish Srivastava, Ruslan Salakhutdinov
Nitish Srivastava, Ruslan Salakhutdinov
[transfer, conference, algorithm, aim, initial] [learning, class, learned, baseline, deep, training, image, superclass, accuracy, convolutional, dataset, test, large, hierarchy, hierarchical, trained, dolphin, performance, visual, well, hidden, good, mir, knowledge, international, learn, based, flickr, input, table, semantic, multimedia, work, labeled, vector, architecture, randomly, multiple, object, boltzmann, unsupervised, average, net, computer, improve, transferring] [tree, structure, improvement, network, node, multimodal, connected, leaf, occurs] [number, method, standard, stochastic, random, gradient] [model, prior, log, data, figure, process] [set, machine, map, note, hard, label] [neural, fully, strong, retrieval]
Convergence of Monte Carlo Tree Search in Simultaneous Move Games
Viliam Lisy, Vojta Kovarik, Marc Lanctot, Branislav Bosansky
Viliam Lisy, Vojta Kovarik, Marc Lanctot, Branislav Bosansky
[game, algorithm, simultaneous, player, mcts, action, strategy, regret, converge, equilibrium, state, formal, eventually, lim, conference, exploitability, sum, current, subgame, utility, repeated, bounded, nash, return, surely, reward, previous, focus, worst, variant, branching, cumulative, exploration, caused, hannan, optimal] [average, randomly, class, based, large] [tree, search, leaf, move, michael, terminal, node] [matrix, convergence, analysis, error, matching, rate, method, empirically, additional, small] [probability, approximate, perfect, figure, monte, carlo, form, time, selected, joint] [selection, empirical, set, lemma, general, denote, consistent, prove, proof, function, case, guaranteed, main] []
Small-Variance Asymptotics for Hidden Markov Models
Anirban Roychowdhury, Ke Jiang, Brian Kulis
Anirban Roychowdhury, Ke Jiang, Brian Kulis
[state, algorithm, sequence, step, sequential, space, follow] [hidden, prediction, accuracy, approach, initialized, training, hierarchical, generative, predicted] [probabilistic, existing, inference, compute, path, update, synthetic] [standard, number, objective, variance, analysis, matrix, supplementary, method, discussion, write, order, bregman] [transition, asymptotics, model, parametric, nonparametric, hmm, distribution, markov, data, joint, time, dirichlet, probability, beam, bayesian, latent, asymptotic, sampler, figure, process, likelihood, observation, segmental, gaussians, mixture, sampling, exponential, family, emission, parameter, nmi, gaussian, hmms, processing, allow, base, considered] [function, cost, map, machine, penalty, set, consider, combinatorial, note] [simple, term]
Reward Mapping for Transfer in Long-Lived Agents
Xiaoxiao Guo, Satinder Singh, Richard L. Lewis
Xiaoxiao Guo, Satinder Singh, Richard L. Lewis
[reward, agent, transfer, optimal, policy, uct, state, orp, planning, conference, packet, sequence, reinforcement, current, initialize, duration, shelter, cmp, food, environment, sequential, space, guidance, routing, reuse, setting, action, previous, utility, incrementally, competing, peter, initial, bounded, algorithm, destination, encourages, expected, andrew, pgrd, decision, step] [task, mapping, performance, learning, domain, approach, international, good, conventional, work, knowledge, evaluation, well, learned, demonstrate, feature, second] [network, node, queue] [objective, method, number, gradient] [time, figure, transition, three, computational, power, inverse, markov] [function, set, problem, consider, machine, cost, linear] [internal, relative, left, location]
DeViSE: A Deep Visual-Semantic Embedding Model
Andrea Frome, Greg S. Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, Tomas Mikolov
Andrea Frome, Greg S. Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, Tomas Mikolov
[conference, space] [visual, softmax, trained, training, semantic, image, embedding, devise, language, imagenet, object, baseline, text, learning, recognition, hierarchical, performance, vector, learned, predict, test, similarity, representation, deep, large, ilsvrc, vision, semantically, labeled, dataset, top, embeddings, output, work, performed, knowledge, layer, table, approach, scale, unannotated, greg, hierarchy, quality, accuracy, based, computer, metric, jeffrey, well, categorization, flat] [network, nearest] [number, random, core, order] [model, data, figure, joint, processing] [label, set, linear, loss, machine] [neural, correct, term, relative, described, novel, presented, simultaneously]
Bayesian Mixture Modelling and Inference based Thompson Sampling in Monte-Carlo Tree Search
Aijun Bai, Feng Wu, Xiaoping Chen
Aijun Bai, Feng Wu, Xiaoping Chen
[action, state, uct, policy, algorithm, thompson, reward, optimal, mcts, return, rollout, planning, mdp, accumulated, online, best, decision, assumption, uncertainty, mdps, current, benchmark, normalgamma, selecting, ctp, mabs, total, racetrack, space, conference, expected, modeled, ucto, exploration, car, goal] [based, approach, learning, knowledge, performed] [search, tree, node, inference, distributed, computation, size] [random, unknown, number, comparing] [distribution, sampling, normal, prior, mixture, bayesian, probability, time, sample, modeling, simulation, dirichlet, transition, posterior, selected, expectation, computational, figure, conjugate, limit, markov, china, data] [function, problem, set, cost, select, linear, general, main, selection, max] [combination]
A* Lasso for Learning a Sparse Bayesian Network Structure for Continuous Variables
Jing Xiang, Seyoung Kim
Jing Xiang, Seyoung Kim
[state, space, optimal, algorithm, goal, benchmark, start, limited, previous, limiting, strategy, conference, stock] [learning, based, score, large, prediction, approach, table, quality, scoring, propose, dataset, work] [search, network, structure, heuristic, stage, ordering, computation, queue, variable, node, path, candidate, size, graph, list, dag, open, directed, parent, nif, larger, improves, pruning, applying, skeleton, smaller] [true, number, method, sparse, optimization, small] [bayesian, time, exact, data, figure, estimate, probability, intermediate, model, equation, continuous, computational, distribution, full] [lasso, set, problem, cost, closed, subset, function, machine, solution] [constraint, reach, estimated, dynamic]
Minimax Optimal Algorithms for Unconstrained Linear Optimization
Brendan McMahan, Jacob Abernethy
Brendan McMahan, Jacob Abernethy
[optimal, minimax, game, player, algorithm, regret, strategy, online, benchmark, unconstrained, betting, adversary, bounded, abernethy, learner, comparator, play, assume, jacob, sequential, best, chooses, difference, round, martingale, sequence, bet, wealth, payoff, choice, sum, selects, interesting, arbitrary, bound] [large, learning, work, appropriate] [characterization, compute, tool, unique] [convex, standard, exactly, random, number, gradient, analysis, order, write, optimization, minimize, descent] [conditional, form, exponential, university, expression, respect, binomial] [theorem, consider, set, loss, function, linear, inf, notion, note, problem, corollary, derive, penalty, result, case, constant, general, implies, paper, polytope, point] []
The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited
Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram
Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram
[total, algorithm, difference] [learning, based, weight, large, approach, table, datasets, labeled, dataset, work, better, class] [clustering, graph, clique, weighted, edge, vertex, structure, balancing, smaller, connected, partition] [hypergraph, cut, hypergraphs, variation, expansion, hyperedge, convex, regularization, standard, extension, method, cuth, matrix, lovasz, spectral, number, ssl, covertype, tvh, hyperedges, minimum, pdhg, optimization, zhou, order, key, error, solve, star, pairwise, zoo] [data, nonlinear, inner, family] [set, proximal, function, min, note, problem, functionals, case, relaxation, max, main, arg, label, solved, ratio, linear] [normalized, corresponding, balanced, functional, fully, contrast, categorical, term]
Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints
Rishabh K. Iyer, Jeff A. Bilmes
Rishabh K. Iyer, Jeff A. Bilmes
[algorithm, greedy, bound, choose, choosing, upper, special, maximizing, bounded, difference, interesting, limited] [based, instance, learning, simpler, speech, vocabulary, class, large, compare, training] [factor, sensor] [optimization, number, iteration, ssc, solve, call, naturally, iterative, empirically] [log, data, extended, form, discrete, investigate] [submodular, approximation, problem, function, set, modular, surrogate, knapsack, cover, guarantee, provide, scsk, cost, scsc, case, lower, tight, curvature, ellipsoidal, machine, framework, subset, theorem, obtains, version, result, hardness, selection, minimizing, general, consider, paper, monotone, solved, eassc, theoretical, bipartite, complexity, main, lin, note, lemma] [constraint, simple, simultaneously, subject]
Generalized Method-of-Moments for Rank Aggregation
Hossein Azari Soufiani, William Chen, David C. Parkes, Lirong Xia
Hossein Azari Soufiani, William Chen, David C. Parkes, Lirong Xia
[algorithm, observe, aggregation, conference, step, agent] [output, better, class, learning, based, technique, large, work, truth, outperforms, performance] [synthetic, ground, david] [rank, pairwise, running, computing, method, faster, matrix, small, order, random] [full, data, figure, model, time, computational, mle, generated, harvard, markov, parameter, university, estimate] [breaking, gmm, consistent, ranking, adjacent, statistical, theorem, kendall, gmms, equivalent, generalized, denote, condition, mse, btl, complexity, sushi, example, set, consistency, corollary, converges, case, prove, linear, hard, conjecture, solution, negahban, azari, provide, machine, parameterized, main, theory, aggregate, gmmgk, lirong] [correlation, recall]
Statistical Active Learning Algorithms
Maria-Florina Balcan, Vitaly Feldman
Maria-Florina Balcan, Vitaly Feldman
[algorithm, setting, computationally, pac, long] [learning, labeled, unlabeled, based, target, concept, accuracy, work, class, unit, corrupted, randomly] [pair] [random, number, error, rate, analysis] [distribution, sample, probability, log, sampling, model, estimate, exponential, simulation, time, dependence, conditioned, parameter, drawn] [active, statistical, tolerance, query, label, passive, function, complexity, theorem, general, machine, framework, halfspaces, homogeneous, set, exists, linear, access, isotropic, note, sqs, tolerant, privacy, hypothesis, point, case, interval, private, balcan, learnhs, easily, actively, problem, simulating, studied, provide, simulate, indicator] [noise, uniform, response, learns, simulated, presence, needed, threshold]
Reshaping Visual Datasets for Domain Adaptation
Boqing Gong, Kristen Grauman, Fei Sha
Boqing Gong, Kristen Grauman, Fei Sha
[action, identify, difference, optimal, total, best, strategy] [domain, datasets, training, target, recognition, test, reshaping, dataset, visual, object, cam, multiple, approach, learning, adapting, table, original, accuracy, image, view, performance, unsupervised, discriminative, category, distinctive, better, dwcv, automatically, large, discover, work, dwcvdomain, achieve, amazon, instance] [source, clustering, discovered, assigned] [number, method, optimization, matching, proposed, practical, reshape] [data, latent, distribution, kernel, prior, form, figure, testing, nonparametric, gaussian, measure, modeling, model] [maximum, set, problem, denote, note, empirical, studied, max, main, label] [adaptation, single, human, activity, maximally, appearance, examine, experimental]
Analyzing Hogwild Parallel Gaussian Gibbs Sampling
Matthew Johnson, James Saunderson, Alan Willsky
Matthew Johnson, James Saunderson, Alan Willsky
[strategy, algorithm, state, sampled] [work, applied] [hogwild, update, local, parallel, diagonally, splitting, lifted, partition, global, understanding, dominant, lifting, inference, scaling, processor, convergent, great] [block, covariance, matrix, convergence, error, iterative, diagonal, analysis, row, small, write, iteration, iterates, solving, number, exactly, written, stochastic] [gibbs, sampling, gaussian, process, exact, model, latent, jacobi, iid, figure, mixing, sampler, equation, allocation, inner, distribution, journal, positive] [linear, theorem, condition, proposition, generalized, consider, solver, provide, outer, case, stability, empirical, approximation] [system, correct, stable, connection, simple, noise]
Manifold-based Similarity Adaptation for Label Propagation
Masayuki Karasuyama, Hiroshi Mamitsuka
Masayuki Karasuyama, Hiroshi Mamitsuka
[step] [aew, hgf, learning, similarity, lnp, based, input, feature, approach, lle, reconstruction, labeled, performance, class, prediction, wij, applied, metric, datasets, second, represented, table, output, test, vector, yale, face, compared, validation] [graph, local, edge, propagation, adjacency, structure, synthetic, laplacian, node, third, mit, median, represent, dii, represents, connected] [error, matrix, number, objective, regularization, method, standard, dimensional, optimization] [data, manifold, figure, model, gaussian, parameter, generated, form, estimation] [label, function, linear, set, theorem, problem, consider] [normalized, interpreted, term]
Parametric Task Learning
Ichiro Takeuchi, Tatsuya Hongo, Masashi Sugiyama, Shinichi Nakajima
Ichiro Takeuchi, Tatsuya Hongo, Masashi Sugiyama, Shinichi Nakajima
[algorithm, optimal, step, programming] [learning, feature, common, approach, training, weight, test, task, input, vector, shared, applied, svm, representation, multiple, formulated, instance, svms, class, handle, ptfl, entire, learn, ith, table] [path, variable] [regularization, matrix, alternating, order, japan, standard, tth, key] [joint, conditional, time, parametric, figure, data, continuous, positive, parameter, journal, independent, model, distribution, sample, three] [quantile, function, ptl, problem, min, set, regression, machine, loss, consider, solution, example, parameterized, selection, bmd, mtl, formulation, minimization, support, condition, arg, independently, cost, linear, continuum] [relative, false, estimated, indicate]
Learning Chordal Markov Networks by Constraint Satisfaction
Jukka Corander, Tomi Janhunen, Jussi Rintanen, Henrik Nyman, Johan Pensar
Jukka Corander, Tomi Janhunen, Jussi Rintanen, Henrik Nyman, Johan Pensar
[chosen, optimal, space, conference, uncertainty, item] [learning, weight, score, level, labeled, well, dataset] [spanning, clique, graph, tree, balancing, network, node, structure, search, edge, chordal, subtrees, graphical, subtree, occurs, rooted, propositional, undirected, junction, connected, cycle, leaf, heart, boolean, occur, induction, finland, pair, path, starting, chordality, econ, smt, characterization, maxsat, candidate, represent] [number, random, optimization, stochastic] [markov, bayesian, model, journal, prior, university, log, form, marginal, distribution, time] [set, maximum, problem, condition, solver, cardinality, lemma, machine, answer, label, statistical, subset, theory] [constraint, encoding, balanced]
A Deep Architecture for Matching Short Texts
Zhengdong Lu, Hang Li
Zhengdong Lu, Hang Li
[decision, space, special, denoted] [architecture, patch, layer, deep, learning, text, based, input, training, short, level, domain, work, mapping, large, bilinear, word, complicated, performance, siamese, deepmatch, hidden, margin, task, semantic, learned, hierarchy, committee, feature, image, similarity, illustrated, activation, second, type, representation, better, randomly, weibo, essentially] [local, parallel, structure, network, product, size, associated, construct] [matching, number, proposed, sparsity, gradient, updating] [model, figure, data, topic, nonlinear, interaction, latent, modeling, form, process] [set, machine, linear, active, effort, answer] [neural, higher, pattern]
Computing the Stationary Distribution Locally
Christina E. Lee, Asuman Ozdaglar, Devavrat Shah
Christina E. Lee, Asuman Ozdaglar, Devavrat Shah
[algorithm, state, walk, space, return, pagerank, bounded, upper, total, bound, assumption, countable, terminates, countably, step, lyapunov, involves, exponentially, relies, chosen, observe] [large, tail, applied] [node, local, computation, size, neighborhood, queue, graph, larger, concentration, neighbor, determine] [random, matrix, number, computing, high, error, method, iteration, true, stochastic, hitting, analysis] [markov, probability, chain, distribution, stationary, time, estimate, transition, monte, carlo, length, respect, power, mixing, positive, sample, sampling, truncated, irreducible, figure] [function, constant, condition, theorem, set, guarantee, provide, terminate, close, general] [greater, stopping, threshold, recurrent]
Nonparametric Multi-group Membership Model for Dynamic Networks
Myunghwan Kim, Jure Leskovec
Myunghwan Kim, Jure Leskovec
[best, state, space, future, step] [performance, based, well, hidden, work, feature, multiple, task, people, prediction] [group, network, link, node, membership, social, death, dmmg, birth, missing, graph, auc, relational, structure, infocom, update, factorial, lfrm, born, lord, linking, explicitly, testll, existing, binary, lfp, pair, merry, belong, kim, tobs, pippin, join] [number, matrix, gradient, performs, analysis, random] [model, time, latent, probability, markov, sampling, data, distribution, sample, drift, figure, process, modeling, three, naive, parameter, nonparametric, transition, posterior, predictive, describe] [active, function, consider, set, dblp, inactive, density] [dynamic, individual, correspond, temporal]
Convex Relaxations for Permutation Problems
Fajwel Fogel, Rodolphe Jenatton, Francis Bach, Alexandre D'Aspremont
Fajwel Fogel, Rodolphe Jenatton, Francis Bach, Alexandre D'Aspremont
[algorithm, sum, focus, optimal] [vector, similarity, table, large, based] [ordering, read, binary, ordered, variable, allows, structural, laplacian, assignment, generate, product, explicitly] [matrix, seriation, spectral, permutation, convex, fiedler, stochastic, doubly, quadratic, write, solving, cut, written, minimize, solves, order, objective, consecutive, solve, symmetric, small, optimization, noisy, true, orthogonal, reg, reorder, eigenvalue, number, siam] [gene, markov, figure, sequencing, positive, data, base, equal, unimodal, chain] [problem, solution, set, linear, combinatorial, relaxation, result, suppose, minimization, lemma, solved, iff, note, proposition, minimizes] [subject, noise, monotonic, corresponding, envelope, recall, produce, connection]
The Fast Convergence of Incremental PCA
Akshay Balsubramani, Sanjoy Dasgupta, Yoav Freund
Akshay Balsubramani, Sanjoy Dasgupta, Yoav Freund
[step, bound, initial, assume, space, sequence, algorithm, martingale, apply, expected, setting, exp] [unit, top, vector, learning, large, work, second] [update, starting, nested] [convergence, rate, incremental, pca, random, oja, analysis, stochastic, vno, krasulina, gradient, covariance, small, method, sphere, principal, descent, coordinate, uniformly, recurrence, pick, remain, expect, matrix, rayleigh, surface, epoch, eigenvectors] [time, data, estimate, sample, probability, form, distribution, including, processing, intermediate, drawn, component] [theorem, lemma, set, suppose, function, machine, result, point, constant, denote, consider, case, deviation, approximation, suitable, proof] [neural, recall, san, potential, pattern, closely]
High-Dimensional Gaussian Process Bandits
Josip Djolonga, Andreas Krause, Volkan Cevher
Josip Djolonga, Andreas Krause, Volkan Cevher
[regret, algorithm, cumulative, bound, assume, bounded, upper, assumption, bandit, sampled, setting, natural, space, best, expensive] [learning, approach, second, vector, learn, score] [optimize, size] [subspace, optimization, matrix, norm, random, noisy, low, true, high, order, recovery, number, rank, error, dimensional, pick, oracle, orthogonal, varies, snf, singular, variance] [bayesian, kernel, gaussian, sampling, process, log, figure, data, estimation, journal, sample, parameter, probability] [function, approximation, linear, set, consider, theoretical, problem, rkhs, machine, note, complexity, point, depend, dimension, prove, theory, isotropic, close, case] [noise, simple, noiseless, incurred, estimated, carefully]
Demixing odors - fast inference in olfaction
Agnieszka Grabska-Barwinska, Jeff Beck, Alexandre Pouget, Peter Latham
Agnieszka Grabska-Barwinska, Jeff Beck, Alexandre Pouget, Peter Latham
[algorithm] [average, wij, based, template, performed, mapping, representation, generative, large, work, complicated] [inference, concentration, network, determine, probabilistic, represent, distributed] [true, small, number, exactly, supplementary, matching, rate] [variational, probability, log, time, sampling, prior, model, approximate, distribution, background, plot, figure, panel, posterior, gamma, university] [set, note, problem, consider, provide, linear] [olfactory, odor, activity, receptor, neural, inferred, drop, absent, correct, realistic, odorant, coding, system, population, bulb, left, complex, presented, course, percentile, divisive, code, digamma, apr, spike, introducing, connectivity, correspond, insight, absence, coffee, reciprocally, false]
Global MAP-Optimality by Shrinking the Combinatorial Search Area with Convex Relaxation
Bogdan Savchynskyy, Jörg Hendrik Kappes, Paul Swoboda, Christoph Schnörr
Bogdan Savchynskyy, Jörg Hendrik Kappes, Paul Swoboda, Christoph Schnörr
[optimal, step, algorithm, programming, initial, called, benchmark, partial] [approach, based, dataset, large, good, scale, datasets, original, table, work, image] [subgraph, graph, local, search, graphical, node, global, allows, plane, size] [convex, method, dual, solve, number, small, solving, order, pairwise, sparse, decomposition, column] [boundary, time, discrete] [combinatorial, problem, relaxation, labeling, solver, energy, arc, solution, potts, min, mrf, consistency, minimization, provide, set, polytope, labelings, theorem, specialized, map, cutting, border, optimality, condition, reparametrized, linear, reparametrization, label, complement, subgraphs, strict, consider, consistent, mplp, idea, strictly, presolve] [corresponding, ieee]
On the Expressive Power of Restricted Boltzmann Machines
James Martens, Arkadev Chattopadhya, Toni Pitassi, Richard Zemel
James Martens, Arkadev Chattopadhya, Toni Pitassi, Richard Zemel
[bounded, bound, free, exponentially, computes, upper, parity] [rbm, hidden, hardplus, output, layer, activation, boltzmann, margin, softplus, rbms, input, large, expressive, learning, deep, represented, unnormalized, maass, type, generative, representational] [network, compute, size, boolean, represent, represents, computed, binary, computable, mass] [symmetric, magnitude, standard, computing, number, basic, error, convex, requires] [probability, log, distribution, restricted, exponential, figure, simulation, form, power, additive] [function, result, thresholded, theorem, lower, construction, approximation, prove, energy, proposition, hajnal, example, provide, machine, note, general, polynomial, constant, bias, paper, case, hard, relate] [neural, threshold, neuron, single, arbitrarily, depends, simple]
Near-optimal Anomaly Detection in Graphs using Lovasz Extended Scan Statistic
James L. Sharpnack, Akshay Krishnamurthy, Aarti Singh
James L. Sharpnack, Akshay Krishnamurthy, Aarti Singh
[computationally, bound, provided, called, electrical] [detection, test, performance, work, type, well, large, distinguish, based, class, knowledge] [graph, network, spanning, binary, edge, degree, sensor, tree, vertex, transitive, developed, size] [random, cut, convex, dual, analysis, arxiv, error, preprint, spectral, minimum] [log, statistic, testing, likelihood, markov, probability, extended, intractable, data, normal, form, positive, university] [scan, effective, theorem, ratio, statistical, corollary, problem, asymptotically, provide, combinatorial, program, submodular, lower, maximum, resistance, relaxation, theoretical, generalized, set, max, hypothesis, anomalous, map, machine, function, consider, theory, introduction, structured] [activity, signal, control, der, uniform, study, ust, ieee, false, potential]
Learning Multiple Models via Regularized Weighting
Daniel Vainsencher, Shie Mannor, Huan Xu
Daniel Vainsencher, Shie Mannor, Huan Xu
[algorithm, robustness, bound, optimal, goal, setting, bounded, appendix] [learning, weight, multiple, approach, common, generalization, average, weighting, well, computer, second, tend] [clustering, weighted, allows] [robust, subspace, number, regularized, minimum, outlier, mode, distance, euclidean, optimization, proposed, alternating, explained, standard, analysis, high, regularization, convex, tailed] [data, model, mixture, base, joint, distribution, journal, figure, generated, sample, association, gaussian, equal] [loss, problem, point, formulation, breakdown, case, lemma, regression, squared, linear, set, theorem, consider, complexity, general, empirical, denote, fat, example, proof, machine, main, close] [ieee, single, uniform, explain, contrast, correct]
Memory Limited, Streaming PCA
Ioannis Mitliagkas, Constantine Caramanis, Prateek Jain
Ioannis Mitliagkas, Constantine Caramanis, Prateek Jain
[algorithm, best, step, assume, goal, optimal, online] [work, large, well, top, performance, tracking, dataset] [size, provably] [covariance, principal, analysis, pca, matrix, variance, streaming, subspace, number, spiked, svd, stochastic, method, singular, explained, recovery, denotes, require, random, norm, incremental, rank, arora, iterate, perpendicular, block, orthogonal, high, performs, standard, store, true, required, pass, spectral] [sample, data, component, probability, model, power, computational, generated, time, estimate, figure, log, journal] [complexity, batch, consider, provide, empirical, proof, note, lemma, theorem, linear, point, constant, case, general, version, theoretical, paper, statistical, close, problem, solution, consistent] [memory, storage, noise, performing]
One-shot learning and big data with n=2
Lee H. Dicker, Dean P. Foster
Lee H. Dicker, Dean P. Foster
[lim, lee, involves, easier] [prediction, learning, large, weak, work, vector, training, object, attention, table, unit, feature, propose] [associated, computed, relevant, smaller, size, factor, third] [error, principal, analysis, method, random, high, oracle, regime, dimensional, low, small, eigenvalue, matrix, additional, number] [component, data, sample, asymptotic, bayesian, journal, model, multivariate, considered, latent, indicates, series] [pcr, theoretical, theorem, empirical, estimator, risk, consistency, proposition, statistical, consistent, regression, paper, studied, consider, linear, compact, annals, suppose, weakly, classical, shrinkage, bias, royal, inf, valid, corollary, apparent, proof, complexity] [suggests, relative, scalar, term, corresponding, study, inconsistent, simple, side]
Distributed k-means and k-median clustering on general communication topologies
Maria-Florina Balcan, Steven Ehrlich, Yingyu Liang
Maria-Florina Balcan, Steven Ehrlich, Yingyu Liang
[algorithm, conference, difference, total, communicate, natural, sampled, round, apply, space] [large, approach, international, entire, amount, based, compare, propose, weight, accuracy, well] [coreset, distributed, local, communication, clustering, weighted, coresets, size, node, global, factor, acm, symposium, sensor, construct, tree, network, partition, annual, portion, graph, send, smaller, spanning, reduce, rooted, message, compute, center] [random, small, low, performs, analysis] [data, log, probability, approximate, figure, sample, grid, central] [cost, set, approximation, construction, solution, lemma, centralized, general, union, constant, proof, provide, note, function, theoretical, exists, theorem] [uniform]
On the Linear Convergence of the Proximal Gradient Method for Trace Norm Regularization
Ke Hou, Zirui Zhou, Anthony Man-Cho So, Zhi-Quan Luo
Ke Hou, Zirui Zhou, Anthony Man-Cho So, Zhi-Quan Luo
[optimal, bound, sequence, assumption, step, algorithm, assume, established, establishes] [performance, vector, approach, learning, class] [passing] [convex, convergence, matrix, trace, norm, pgm, error, kkf, operator, gradient, rank, method, regularization, singular, objective, rate, solving, key, spectral, square, optimization, analysis, decomposition, exist, projection, standard, hgk, luo, krkkf, tseng, order] [form, residual, figure, parameter] [loss, solution, linear, set, problem, proposition, function, proof, theorem, implies, lemma, lipschitz, exists, point, case, proximal, constant, converges, suppose, consider, compact, lipschitzian, min, prove, machine, map, subsequence, note, result, engineering, shrinkage, convexity] [desired, strong]
Learning and using language via recursive pragmatic reasoning about other agents
Nathaniel J. Smith, Noah Goodman, Michael Frank
Nathaniel J. Smith, Noah Goodman, Michael Frank
[previous, uncertain, game, uncertainty, assume, agent, optimal, assumption, current, fact, making, goal, rational, strategy] [learning, language, word, reasoning, good, object, work, learn, conventional, common, mapping, acquisition, based] [inference, recursive, communication, evidence, recursion, iterated] [] [model, prior, data, allow, probability, university] [set, consider, provide, result] [pragmatic, listener, speaker, lexicon, novel, literal, scalar, horn, system, behavior, refer, implicature, communicative, bad, cognitive, meaning, referring, implicatures, disambiguation, despite, refers, interpret, fully, ate, uniform, experimental, partner, literally, stable, correct, understands, simple, human, early, emergence, referential]
Reinforcement Learning in Robust Markov Decision Processes
Shiau Hong Lim, Huan Xu, Shie Mannor
Shiau Hong Lim, Huan Xu, Shie Mannor
[algorithm, policy, adversarial, regret, minimax, mdp, state, total, reward, decision, check, action, uncertainty, executed, bound, optimistic, adversary, optimal, assume, chosen, purely, setting, mdps, episode, expected, step, horizon, online, fails, best, singapore, choice, olrm, previous, start, reinforcement, difference] [learning, performance, average, challenge, well, large] [pair, existing] [stochastic, robust, number, unknown, phase, additional, true, supplementary, key, epoch, lead, computing] [markov, transition, figure, probability, log, parameter] [set, case, result, proof, main, lemma, consider, theorem, problem, min, function, machine, note, suppose, example, max, paper, framework] [behavior, change, arbitrarily, actual]
Stochastic Optimization of PCA with Capped MSG
Raman Arora, Andy Cotter, Nati Srebro
Raman Arora, Andy Cotter, Nati Srebro
[algorithm, mirror, online, step, optimal, fact, conference] [well, approach, learning, good, based, vector, compare, view, essentially, maximize] [update, runtime, larger, distinct] [msg, stochastic, pca, capped, matrix, rank, incremental, projection, subspace, gradient, warmuth, objective, iterates, convex, optimization, sgd, iteration, descent, iterate, project, analysis, eigendecomposition, method, suboptimal, standard, arora, stuck, kuzmin, requires, frobenius, implementation, variance, suboptimality, eigenvectors, theoretically, covariance] [data, distribution, figure, sample, computational, probability] [problem, approximation, solution, feasible, set, empirical, dimension, consider, machine, lemma, theoretical, linear, function, optimum, point] [constraint, corresponding, study, memory, potential, subject, refer]
Bellman Error Based Feature Generation using Random Projections on Sparse Spaces
Mahdi Milani Fard, Yuri Grinberg, Amir massoud Farahmand, Joelle Pineau, Doina Precup
Mahdi Milani Fard, Yuri Grinberg, Amir massoud Farahmand, Joelle Pineau, Doina Precup
[bellman, state, algorithm, policy, space, bound, assume, difference, reinforcement, choice, apply, bounded, logarithmic, optimal, parr, prj, online] [feature, large, generation, prediction, based, learning, original, compare, better, vector, evaluation] [size, smaller, induced, generate, factor, preserve] [error, random, compressed, projection, sparse, number, analysis, norm, bebfs, method, gradient, lstd, basis, small, variance, scbebf, high, expect, bebf, dimensional, regularized, matrix, iteration, reduction, cbebf, order, fast] [sample, time, estimate, processing, log, observed, estimation, observation, process, figure, probability] [function, linear, regression, approximation, set, machine, lemma, provide, note, general, empirical, theorem, complexity] [temporal, neural, signal, memory]
Recurrent networks of coupled Winner-Take-All oscillators for solving constraint satisfaction problems
Hesham Mostafa, Lorenz. K. Mueller, Giacomo Indiveri
Hesham Mostafa, Lorenz. K. Mueller, Giacomo Indiveri
[state, optimal, satisfy, oscillation] [bottom, input, top, average, large, good, architecture, work] [network, variable, search, stage, local, cycle, implemented, coupled, evidence, binary, assignment, represent] [phase, number, proposed, solving, solve, rate, high, order] [time, limit, model, process, figure, plot, sample, intermediate] [consistent, problem, solution, point, selection, energy, function, perturbation] [wta, population, activity, external, constraint, neural, excitatory, neuronal, fully, recurrent, behavior, coupling, xor, oscillatory, internal, winner, stable, neuromorphic, violated, satisfaction, middle, dynamical, circuit, inhibitory, equally, rule, biological, change, connectivity, winning, ten, needed]
On Flat versus Hierarchical Classification in Large-Scale Taxonomies
Rohit Babbar, Ioannis Partalas, Eric Gaussier, Massih-Reza Amini
Rohit Babbar, Ioannis Partalas, Eric Gaussier, Massih-Reza Amini
[bound, strategy, best, decision, denoted] [hierarchical, mlr, hierarchy, class, training, generalization, datasets, large, taxonomy, learning, svm, international, ipc, scale, table, well, reported, trained, category, gfb, explanation, based, original, learned, feature, better, propose, performance, accuracy, average, text, target] [node, pruning, size, prune, associated, root, pruned] [error, number, random, matrix, denotes] [asymptotic, probability, posterior, data, likelihood, processing, three, positive] [set, theorem, empirical, complexity, function, rademacher, problem, multiclass, ratio, theoretical, maximum, example, rely, consider, version, machine, lemma, close] [suggests, term, preferred, simple, neural, fully]
Learning Gaussian Graphical Models with Observed or Latent FVSs
Ying Liu, Alan Willsky
Ying Liu, Alan Willsky
[algorithm, greedy, best, appendix, step] [learning, learned, second, propose] [fvs, size, graph, tree, fvss, inference, spanning, graphical, ggms, ggm, structure, compute, subgraph, node, larger, computed, corresponds, represent, departure] [matrix, covariance, exactly, small, divergence, random, true, projection, number, sparse, proposed, alternating, accelerated, unknown, project] [latent, observed, distribution, model, family, figure, exact, log, gaussian, modeling, time, data, conditioned, conditional, marginal, estimate, approximate, inverse, markov, full, three, selected] [complexity, empirical, set, problem, function, maximum, provide, machine, min, arg, proposition, note] [feedback, study, capacity, ieee]
Bayesian inference as iterated random functions with applications to sequential inference in graphical models
Arash Amini, Xuanlong Nguyen
Arash Amini, Xuanlong Nguyen
[algorithm, sequence, sequential, assume, optimal, assumption, michigan, deterministic, absolute, goal] [based, multiple, detection, shared] [graphical, inference, iterated, distributed, variable, illustrates, allows, occurred, network, message, binary, recursion, underlying] [convergence, random, norm, analysis, iteration, write, key, operator, fast, application, minimum] [approximate, posterior, exact, probability, bayesian, time, model, data, distribution, latent, prior, log, independent, bayes, conditioned, observed, form] [point, theorem, general, problem, note, consider, theory, example, classical, function, lipschitz, main, lemma, constant, proof, complexity, approx, paper, geometric, irf, semigroup, analyze, denote, tex, provide] [change, rule, recall, property, stopping, ieee]
On the Relationship Between Binary Classification, Bipartite Ranking, and Binary Class Probability Estimation
Harikrishna Narasimhan, Shivani Agarwal
Harikrishna Narasimhan, Shivani Agarwal
[regret, transfer, algorithm, optimal, bound, goal, assumption, upper, setting, expected, converted, satisfy] [training, learning, good, weak, learned, learn, class, based, performance, second, directly, randomly, roc] [binary, increasing, construct, size, synthetic] [error, transform, small, standard, additional, remark, denotes] [model, data, distribution, probability, sample, drawn, parameter, journal, figure, three, estimation, iid] [ranking, cpe, bipartite, theorem, consistent, function, cost, machine, result, regression, calibrated, statistically, empirical, access, note, squared, linear, logistic, regretrank, monotonically, suitable, isotonic, constructed, proof, derive, regretsq, ersq, annals, set, problem, errank, composing] [threshold, area, uniform, described, curve]
On Algorithms for Sparse Multi-factor NMF
Siwei Lyu, Xin Wang
Siwei Lyu, Xin Wang
[algorithm, multiplicative, optimal, sum, total, initial] [based, work, target, original, second, better, applied] [factor, product, update, global, real, synthetic] [matrix, nonnegative, mfnmf, stochastic, sparse, nmf, objective, sparsity, column, optimization, mkl, divergence, factorization, xkl, norm, diagonal, vij, solving, number, iterative, analysis, solve, decomposition, intuitive, cij, afford, gradient, updating, require, constrained, incorporate, method, fun, supplementary] [log, dirichlet, three, data, form, parameter, model] [problem, solution, case, regularizer, function, lemma, generalized, point, max, constant, set, general, result, formulation, proof, note, reduces] [simple, term, corresponding, study, correspond]
Neural representation of action sequences: how far can a simple snippet-matching model take us?
Cheston Tan, Jedediah M. Singer, Thomas Serre, David Sheinberg, Tomaso Poggio
Cheston Tan, Jedediah M. Singer, Thomas Serre, David Sheinberg, Tomaso Poggio
[action, actor, current, sensitive, difference, sum] [visual, better, representation, recognition, invariant, performed, average, good, predicted, input, well, level, short, computer, vision, window, pixel] [weighted] [high, number, matching, averaged] [model, processing, form, figure, journal, time, prior] [invariance, linear, consistent, simply, example] [neural, ventral, dorsal, sts, stream, temporal, response, monkey, neuron, motion, encoding, superior, population, macaque, individual, simple, performing, snippet, biological, combination, system, calculated, area, single, cortex, correlation, brain, pattern, sulcus, produce, static, singer, human, actual, stimulus, selective, reproduce, range, preferred, ieee, bank, perception]
Large Scale Distributed Sparse Precision Estimation
Huahua Wang, Arindam Banerjee, Cho-Jui Hsieh, Pradeep Ravikumar, Inderjit Dhillon
Huahua Wang, Arindam Banerjee, Cho-Jui Hsieh, Pradeep Ravikumar, Inderjit Dhillon
[algorithm, step, assume, optimal] [large, scale, achieve, work, compare, performance, score, tiger, table, shared] [distributed, size, parallel, structure, node, scalable, assigned, graph, cache, scalability, existing, computation, synthetic, increasing] [matrix, block, column, sparse, precision, covariance, clime, speedup, core, number, multiplication, admm, small, method, sparsity, solve, convergence, solving, optimization, high, cyclic, alternating, rank, xij, low, constrained, random, direction, inexact, elementwise, scol, dimensional, solves, rate] [figure, sample, data, estimation, process, time, distribution, estimate, grid, inverse] [framework, linear, statistical, support, consider, machine, theorem] [memory, single, load]
Parallel Sampling of DP Mixture Models using Sub-Cluster Splits
Jason Chang, John W. Fisher III
Jason Chang, John W. Fisher III
[space, algorithm, current, sampled, initial, converge] [work, multiple, hierarchical, vector, based] [cluster, split, merge, graphical, dpmm, inference, parallel, merges, detailed, parallelizable, dpmms, concentration, balance, regular, represent, larger] [proposed, convergence, number, method, random, denotes] [dirichlet, data, mixture, sampling, sampler, auxiliary, restricted, process, gibbs, distribution, figure, model, chain, mcmc, markov, proposal, augmented, sample, conjugate, posterior, prior, equation, bayesian, hastings, form, journal, probability, conditioned, ergodic, monte, carlo, approximate, parameter, joint, exact] [point, consider, ratio, note, result, label, set, statistical] [corresponding, supplement]
Trading Computation for Communication: Distributed Stochastic Dual Coordinate Ascent
Tianbao Yang
Tianbao Yang
[variant, algorithm, bound, optimal, step, sampled] [learning, work, based, training, compare, randomly] [distributed, computation, communication, increasing, global, local, size, variable] [dual, disdca, practical, stochastic, number, convergence, admm, tradeoff, solving, iteration, basic, coordinate, comparison, descent, convex, ascent, updated, gradient, gap, analysis, alternating, method, optimizing, duality, updating, direction, optimization, norm, running, regularized, sdca, proposed, sgd, aggressive, supplementary, subproblem, dca, covtype, scl] [data, parameter, figure, continuous, time] [loss, function, problem, cost, machine, solution, primal, verify, smooth, hinge, effective, linear, note, penalty, denote, theorem] [presented, region, varying, increase, fashion]
Prior-free and prior-dependent regret bounds for Thompson Sampling
Sebastien Bubeck, Che-Yu Liu
Sebastien Bubeck, Che-Yu Liu
[thompson, regret, bubeck, reward, step, policy, arm, bpr, optimal, best, bandit, strategy, setting, exp, bound, bounded, algorithm, agrawal, attains, conference, audibert, brn, agent, assumption, decompose, goyal, russo, assume, roy, round, maximal, fact] [learning, sense, view, well, second, precisely, performance] [product, beta, distributed, annual] [random, uniformly, stochastic, variance, analysis, numerical] [sampling, prior, bayesian, figure, distribution, log, time, probability, gaussian, posterior, respect] [problem, consider, proof, result, interested, inequality, paper, theory, case, theorem, implies, note, easy, machine, max, obtains, constant, denote, empirical, lower] [control, inspired, term, individual, simple, described]
Structured Learning via Logistic Regression
Justin Domke
Justin Domke
[algorithm, current, sampled, previous, decision] [learning, training, mlp, boosting, vector, image, segmentation, class, input, denoising, work, object, representation, boosted, test, prediction] [inference, tree, local, optimize, decomposes, meshi] [gradient, optimization, stochastic, iteration, standard, dual, updating, random, convergence, alternating, solving, pairwise, objective, minimize, write] [univariate, respect, entropy, form, joint, conditional, log, nonlinear, figure] [linear, function, problem, logistic, max, set, regression, loss, structured, energy, arg, min, maximization, select, consider, example, fij, exists, result, equivalent, general, approximation, paper, theorem, minimization, constant, solution, easily] [performing, consisting, term]
Learning to Prune in Metric and Non-Metric Spaces
Leonid Boytsov, Bilegsaikhan Naidan
Leonid Boytsov, Bilegsaikhan Naidan
[space, conference, algorithm, decision, applicable, visit] [metric, similarity, performance, table, international, learning, large, learned, based, indexing, approach, sift, work] [search, nearest, neighbor, pruning, triangle, prune, partition, acm, vldb] [distance, method, proposed, permutation, dimensionality, lsh, bregman, pivot, cayton, hash, rank, analysis, faster, number, proximity, bbtree, bucket, small, classic, termination, fast, slower, sphere, order] [data, approximate, time, grid, sampling, processing, exact, figure] [function, query, machine, set, case, approximation, point, effective, procedure, linear] [retrieval, intrinsic, recall, ieee, pattern, left, early, searching, correlation]
Near-Optimal Entrywise Sampling for Data Matrices
Dimitris Achlioptas, Zohar S. Karnin, Edo Liberty
Dimitris Achlioptas, Zohar S. Karnin, Edo Liberty
[bound, algorithm, fact, optimal, bernstein, previous, step, item, quantity] [work, good, quality, approach, large, top] [factor, sketch, computation, smaller, concentration] [matrix, number, random, small, pij, row, entry, aij, norm, error, expect, fast, column, spectral, streaming, dimitris, method, arxiv, singular, petros, order, typically, largest, achlioptas, minimize, strongest] [distribution, sampling, data, probability, sample, measure, independent, element, form, trend, respect] [theorem, max, minimizing, condition, note, approximation, result, ratio, theory, lemma, consider, linear, budget, function, satisfying, point] [needed, simple, left, single, highly, ieee, completely, depends, corresponding]
Online learning in episodic Markovian decision processes by relative entropy policy search
Alexander Zimin, Gergely Neu
Alexander Zimin, Gergely Neu
[policy, state, online, learner, algorithm, regret, bandit, decision, occupancy, setting, total, episode, episodic, bound, environment, mdp, conference, neu, space, assume, action, expected, previous, step, markovian, called, difference, upper, observes, selects, assumption, concerning, reinforcement, deterministic, suffered, mdps, goal] [learning, work, propose, based, original, international] [search, path, factor, shortest] [optimization, analysis, stochastic, consecutive, solving, minimize, projection] [log, full, entropy, markov, time, measure, transition, equation, stationary, interaction, describe, generated, positive] [problem, loss, function, case, theorem, consider, proof, set, min, arg, point, machine, linear, lemma, proposition, theory, select] [relative, assuming, change]
A Latent Source Model for Nonparametric Time Series Classification
George H. Chen, Stanislav Nikolov, Devavrat Shah
George H. Chen, Stanislav Nikolov, Devavrat Shah
[setting, conference, grows, decision, assume, follow, observing, vote, observe, replace] [training, learning, performance, international, classify, detection, labeled, work, achieve, based] [weighted, source, nearest, existing, synthetic, size, acm, neighbor] [number, rate, error, true, gap, small, unknown, distance] [time, series, latent, majority, data, voting, twitter, model, topic, log, mixture, gaussian, trending, news, figure, trend, probability, positive, parameter, observed, sample, spherical, generated, allowed, estimate, advance, forecasting, journal, classifier] [label, theoretical, map, set, access, generalized, correctly, example, result, case, maximum, denote, version, guarantee, close] [noise, early, activity, false, experimental, neural]
Binary to Bushy: Bayesian Hierarchical Clustering with the Beta Coalescent
Yuening Hu, Jordan Boyd-Graber, Hal Daume III, Z. Irene Ying
Yuening Hu, Jordan Boyd-Graber, Hal Daume III, Z. Irene Ying
[sequential, duration, initial, natural, belief, brownian, total] [hierarchical, feature, based, propose, hierarchy, better, common, discover] [coalescent, beta, dpmm, tree, clustering, inference, node, subtree, bushy, diffusion, edge, merge, message, parent, binary, synthetic, smc, event, singleton, propagation, considers, coalescents, cluster, real, dpmms, structure, subsumer, root, kingman, size, concentration, partition, bushier, local] [rate, number, true, analysis, performs] [distribution, data, dirichlet, time, bayesian, transition, proposal, probability, three, figure, process, kernel, model, particle, monte, base, observed, carlo, latent, equation, prior, sample, parameter, restriction, modeling, posterior, component, gaussian, measure, length] [set, consider] [human, internal, biological]
Data-driven Distributionally Robust Polynomial Optimization
Martin Mevissen, Emanuele Ragnoli, Jia Yuan Yu
Martin Mevissen, Emanuele Ragnoli, Jia Yuan Yu
[uncertainty, optimal, uncertain, setting, assumption, sequence, deterministic, programming, decision, assume, conservative] [vector, work, learning, appear, table] [network, node, associated, construct, degree] [robust, optimization, order, number, unknown, basic, method, solving, objective, error, random, solve] [probability, histogram, distribution, multivariate, parameter, estimate, univariate, data, estimation, moment, form, model, markov] [set, polynomial, density, problem, distributional, distributionally, function, case, min, solution, consider, sdp, denote, demand, theorem, water, closed, suppose, dro, max, semialgebraic, sdpr, constructed, pressure, machine, counterpart, consistency, corollary, ibm, example, guarantee, statistical, hard, exists, empirical, classical, risk, relaxation] [estimated, contrast]
Improved and Generalized Upper Bounds on the Complexity of Policy Iteration
Bruno Scherrer
Bruno Scherrer
[policy, state, mdp, terminates, optimal, bound, deterministic, assumption, decision, discount, fact, sequence, action, contraction, mdps, upper, space, lim, deduce, vmax, maximal, greedy, appendix, discounted, simplex, algorithm, advantage, involves, contracting, mentionned, best, expected, called] [vector, class, well] [factor, cycle, structural, improvement] [number, iteration, analysis, stochastic, call, write, require, operator, convergence, required] [log, respect, time, markov, positive, equation, dependency, exponential, stationary, measure] [lemma, result, theorem, max, proof, polynomial, set, complexity, problem, consider, linear, lower, implies, exists, satisfying, function] [recurrent, transient, control, term, needed, uniform]
Transfer Learning in a Transductive Setting
Marcus Rohrbach, Sandra Ebert, Bernt Schiele
Marcus Rohrbach, Sandra Ebert, Bernt Schiele
[transfer, space, provided, setting, exploit] [learning, training, approach, semantic, knowledge, image, similarity, recognition, labeled, representation, raw, mpii, performance, object, propagated, datasets, yahoo, awa, improve, unlabeled, work, large, imagenet, category, accuracy, pst, test, direct, class, based, achieve, trained, visual, quality, output, dataset, instance, metric, unseen, manual, mined, supervised, linguistic, compare, feature, good, adapt, script, enable, scale] [graph, structure, neighborhood, propagation, local, web] [number] [figure, data, intermediate, three] [label, composite, provide, set, note] [novel, attribute, external, activity]
Bayesian optimization explains human active search
Ali Borji, Laurent Itti
Ali Borji, Laurent Itti
[interpolation, algorithm, optimal, choose, best, uncertainty, strategy, step] [learning, training, better, task, test, randomly, performance, accuracy, average, closer, well, visual, approach, experiment, learn] [search, global, perform, local, degree] [optimization, random, distance, standard, number, gradient, analysis, basic, rate] [bayesian, gaussian, figure, model, selected, process, sample, data] [function, active, maximum, max, point, selection, deviation, lower, theoretical, set, design, provide] [human, std, click, location, extrapolation, higher, hit, actual, searched, trial, xtolm, asked, behavior, normalized, guess, agreement, rise, chose, maxitr, progressively]
Distributed Representations of Words and Phrases and their Compositionality
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, Jeff Dean
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, Jeff Dean
[natural, best, conference, space] [word, training, vector, language, softmax, hierarchical, frequent, learning, negative, phrase, table, large, accuracy, learned, trained, nce, task, reasoning, analogical, work, based, quality, performance, google, analogy, mnih, tomas, introduced, billion, compositionality, capital, international, mikolov, representation, better, dataset, mountain, view, context, semantic, learn, speech, good, yoshua, lufthansa, collobert, well, sentence, evaluate, rare] [network, size, represent, structure, distributed, recursive] [subsampling, method, objective] [model, data, sampling, log, contrastive, probability, estimation, processing, continuous, news, distribution] [linear, paper, set, machine, result, closest, formulation] [neural, simple, noise, frequency]
Analyzing the Harmonic Structure in Graph-Based Learning
Xiao-Ming Wu, Zhenguo Li, Shih-Fu Chang
Xiao-Ming Wu, Zhenguo Li, Shih-Fu Chang
[upper, setting, assume, state, step, bounded] [labeled, target, unlabeled, large, learning, wik, table, wij, compare, instance, class, well, vector] [graph, structure, laplacian, vertex, global, starting, green, local, partially, von, degree, understanding, larger] [harmonic, random, analysis, hitting, cut, absorption, absorbing, eigenvectors, variation, superlevel, parw, regularization, gap, commute, comparing, number, proposed, small, spectral, call, absorbed, magenta, conductance, key] [probability, data, observation] [function, loss, denote, corollary, set, lemma, point, theorem, arg, consider, sorted, note, lower, ratio, exists, result] [normalized, examine, drop, capture, desired, hit, superior]
Regularized Spectral Clustering under the Degree-Corrected Stochastic Blockmodel
Tai Qin, Karl Rohe
Tai Qin, Karl Rohe
[algorithm, expected, step, previous, bound] [average, performance, experiment, unit, large] [node, rsc, degree, clustering, graph, blockmodel, sbm, edge, network, adjacency, partition, dii, planted, laplacian, heterogeneous, membership, cluster, community, political, underlying, projecting, karrer, scp] [spectral, matrix, leverage, stochastic, block, row, regularized, regularization, number, analysis, rate, minimum, random, diagonal, standard, small, eigenvectors, sphere, largest, proposed, orthogonal, high] [probability, figure, three, parameter, data, estimation, form, positive, panel, journal] [theorem, set, statistical, lemma, empirical, constant, paper, close, denote, chaudhuri, corollary, version, point, consider] [population, study, corresponding, threshold, left]
It is all in the noise: Efficient multi-task Gaussian process inference with structured residuals
Barbara Rakitsch, Christoph Lippert, Karsten Borgwardt, Oliver Stegle
Barbara Rakitsch, Christoph Lippert, Karsten Borgwardt, Oliver Stegle
[sum, period] [task, prediction, hidden, training, performance, evaluation, learning, shared, common, learnt, compared, second, performed, measured] [runtime, causal, inference, strength, structure, product] [covariance, matrix, number, standard, proposed, implementation] [model, gaussian, process, kronecker, sample, vec, parameter, observed, expression, independent, likelihood, data, considered, kernel, gene, predictive, latent, marginal, modeling, form, multivariate, naive, log, arabidopsis, computational, yeast, residual, figure, derived, thaliana, relatedness, simulation, selected, iid, observation, joint, investigate] [structured, linear, function, machine, empirical, regression, statistical] [noise, signal, correlation, unobserved, simulated, single, sharing, complex]
Embed and Project: Discrete Sampling with Universal Hashing
Stefano Ermon, Carla P. Gomes, Ashish Sabharwal, Bart Selman
Stefano Ermon, Carla P. Gomes, Ashish Sabharwal, Bart Selman
[algorithm, bound, space, complete, worst, chosen, return, belief] [based, accuracy, weight, large, instance, output, technique, generation, randomly, embedding, test, representation, computer] [search, factor, graphical, feasibility, software, weighted, local, increasing, underlying] [hash, number, uniformly, optimization, random, true, high, error, pairwise] [sampling, probability, distribution, sample, discrete, mcmc, marginals, independent, ising, figure, count, time, chain, family, marginal, counting, exponential, gibbs, model, accurate] [combinatorial, problem, set, lemma, discretization, function, case, constant, hard, procedure, universal, consider, solver, ibm, provide, carla, maxx, rejection, bart] [uniform, produced, desired, estimated, produce]
Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses
Harish G. Ramaswamy, Shivani Agarwal, Ambuj Tewari
Harish G. Ramaswamy, Shivani Agarwal, Ambuj Tewari
[space, expected, computationally, conference] [mapping, target, learning, explicit, prediction, training, vector, international, type, learn, average, consists, large, weight, instance, performance, relevance] [associated, science, graph, yij] [convex, rank, denotes, matrix, pairwise, calibration, permutation, order, number, optimization, transform] [probability, model, document, family, respect, distribution, sample, including] [surrogate, loss, calibrated, subset, ranking, result, consistency, function, set, map, inf, theorem, pred, case, min, problem, general, construction, statistical, machine, ramaswamy, note, label, simply, agarwal, dimension, duchi, example, converges, minimizing, predpd, preinforce, multiclass] [noise, position, sorting]
Adaptive Market Making via Online Learning
Jacob Abernethy, Satyen Kale
Jacob Abernethy, Satyen Kale
[market, price, strategy, regret, algorithm, best, making, bounded, trader, round, stock, cash, inventory, assume, bound, total, period, trading, sell, buy, current, online, mmmw, hpq, sequence, conference, difference, wmt, multiplicative, expert, msft, maker, execute, liquidity, quoted, spread, mmfpl, setting] [learning, window, performance, work, based, class, prediction, well, large] [update] [order, low, number, transaction, analysis] [time, limit, model, distribution, data] [lemma, set, consider, theorem, prove, design, portfolio, universal, problem, case, framework, risk, corollary, proof, stated, place, simply, combinatorial] [change, simple]
Zero-Shot Learning Through Cross-Modal Transfer
Richard Socher, Milind Ganjoo, Christopher D. Manning, Andrew Ng
Richard Socher, Milind Ganjoo, Christopher D. Manning, Andrew Ng
[space, transfer, natural] [unseen, image, word, semantic, class, accuracy, training, learning, vector, visual, novelty, mapped, test, cat, unsupervised, work, feature, performance, knowledge, mapping, detection, learn, predict, classify, domain, object, based, context, deep, train, dog, distractor, achieve, achieved, approach, dataset, original, large, trained, better, softmax, category, language, visualization, pipeline, second, learned, compare, truck] [nearest, determine, network, assign, local, probabilistic] [outlier, method, high, standard, number, analysis] [model, probability, gaussian, data, figure, bayesian, manifold] [set, distributional, function, close, point, map] [loop, neural, corresponding, attribute, single, threshold]
Reasoning With Neural Tensor Networks for Knowledge Base Completion
Richard Socher, Danqi Chen, Christopher D. Manning, Andrew Ng
Richard Socher, Danqi Chen, Christopher D. Manning, Andrew Ng
[previous, introduce, special, goal] [word, entity, knowledge, vector, accuracy, reasoning, training, relationship, wordnet, work, triplet, learning, layer, freebase, bilinear, scoring, common, semantic, francesco, large, initialized, type, multiple, nationality, compare, predict, randomly, instance, unsupervised, based, score, table, trained, learn, male, gender, ntn, tiger, unseen, slice, florence, predicting, second, train, corrupted, dataset] [relation, network, relational, initialization, represent, existing, allows, recursive] [tensor, number, standard, random, matrix, distance, comparison, order] [model, base, testing, figure, data, restricted, interaction] [set, database, case, function, example, answer, statistical, linear] [neural, single, correct, sharing, higher]
Spike train entropy-rate estimation using hierarchical Dirichlet process priors
Karin C. Knudson, Jonathan Pillow
Karin C. Knudson, Jonathan Pillow
[long, state, sequence, choose, previous, choosing, choice, limited, fact] [hierarchical, context, large, train, short, based, amount, compare, hierarchy, better, ability] [binary, depth, tree, beta, structure, size, existing, associated, represents, matter] [rate, block, stochastic, true, number, random, shorter] [entropy, transition, data, markov, bayesian, prior, probability, model, process, estimate, time, distribution, hdp, figure, posterior, dirichlet, length, symbol, chain, equation, sample, estimation, lengthentropy, longer, measure, bayes, hemphdp, computational, considered, gibbs] [estimator, empirical, statistical, estimating, note, consider, set] [spike, neural, simulated, fully, estimated, property, calculated, calculate]
On the Sample Complexity of Subspace Learning
Alessandro Rudi, Guillermo D. Canas, Lorenzo Rosasco
Alessandro Rudi, Guillermo D. Canas, Lorenzo Rosasco
[bound, space, best, choice, upper, expected, span] [learning, reconstruction, embedding, performance, feature, top, knowledge, metric, unit, unsupervised] [associated, computed, compute, increasing] [subspace, rate, decay, pca, covariance, error, order, distance, spectral, eigenvalue, operator, dimensionality, random, high, plateau, convergence, regularization, matrix, number, spectrum, principal, reduction, remark] [estimate, kernel, log, hilbert, probability, data, figure, estimation, equation, form, component, sample, family] [support, empirical, theorem, note, problem, function, corollary, linear, main, machine, case, dimension, minimizes, lemma, classical, general, consider, theory, suitable, polynomial, condition, approximation, sharper] [threshold, interest, behavior, neural, novel]
Low-rank matrix reconstruction and clustering via approximate message passing
Ryosuke Matsushita, Toshiyuki Tanaka
Ryosuke Matsushita, Toshiyuki Tanaka
[algorithm, initial, belief, involves, achieves, exp, state] [accuracy, reconstruction, performance, based, second, international] [clustering, cluster, message, passing, assigned, structural, datum, icm, marginalization, local, propagation, assignment, global, evolution, symposium] [amp, matrix, proposed, number, method, iteration, minimum, factorization, true, rank, random, numerical, analysis, additional] [distribution, bayesian, posterior, variational, data, approximate, prior, bayes, marginal, estimation, log, gaussian, positive, derived, limit, figure, estimate, computational] [problem, map, arg, maximum, consider, min, loss, minimization, function, case, approximation, set, machine, approximated, suppose] [ieee, calculate, normalized, calculation, needed, noise]
More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server
Qirong Ho, James Cipar, Henggang Cui, Seunghak Lee, Jin Kyu Kim, Phillip B. Gibbons, Garth A. Gibson, Greg Ganger, Eric Xing
Qirong Ho, James Cipar, Henggang Cui, Seunghak Lee, Jin Kyu Kim, Phillip B. Gibbons, Garth A. Gibson, Greg Ganger, Eric Xing
[algorithm, bounded, state, conference, assume] [shared, work, well, large, multiple, computer, table, performance] [ssp, staleness, server, stale, worker, distributed, thread, ssptable, clock, bsp, parallel, network, waiting, synchronous, cache, asynchronous, computation, slowest, vms, versus, read, wait, bulk, mod, async, compute, fastest, missing, iter, freshness, progress, spend, correctness] [objective, matrix, convergence, gradient, descent, stochastic, iteration, number, noisy, faster, row, rate, implementation] [time, data, model, parameter, topic, full, lda, process, figure, modeling] [lasso, function, machine, consistency] [system]
Deep Neural Networks for Object Detection
Christian Szegedy, Alexander Toshev, Dumitru Erhan
Christian Szegedy, Alexander Toshev, Dumitru Erhan
[apply, total, algorithm] [object, image, bounding, box, detection, mask, training, dnn, learning, output, class, score, approach, large, convolutional, deep, trained, localization, well, computer, localizer, scale, multiple, layer, input, train, window, performance, negative, vision, second, detectornet, truth, sliding, applied, compositional, deformable, test, resolution, international, ined, work, predict, discriminatively, covered, precisely, top, based] [network, size, inference, generate, stage, ground, binary, smaller, larger, perform] [number, small, precision] [full, model, time, considered, positive, figure] [set, regression, problem, machine, cost] [neural, pattern, pascal, higher, produce]
Variational Planning for Graph-based MDPs
Qiang Cheng, Qiang Liu, Feng Chen, Alex Ihler
Qiang Cheng, Qiang Liu, Feng Chen, Alex Ihler
[algorithm, decision, policy, mdp, mdps, reward, factored, planning, state, expected, optimal, programming, fvi, best, marketing, alp, api, exp, belief, yck, management, dck, advantage, crop, bellman, exponentially, assume, making, conference] [represented, table, large, better, representation, based, directly] [local, cluster, viral, liu, disease, structure, graph, ihler, size, propagation, regular, compute, variable, social, product] [iteration, number, solving, stochastic, solve] [variational, approximate, markov, log, transition, distribution, form, exact, marginal, exponential, entropy, full, additive, equation, figure, university] [function, framework, linear, set, solved, structured, solution, max, complexity, consider, provide] [constraint, system, dynamic]
Learning a Deep Compact Image Representation for Visual Tracking
Naiyan Wang, Dit-Yan Yeung
Naiyan Wang, Dit-Yan Yeung
[online, state, fail, best, previous, provided, sum] [tracking, object, image, learning, visual, tracker, video, tracked, deep, dlt, learn, numbercenter, tld, challenging, generative, approach, denoising, discriminative, training, autoencoder, layer, sdae, feature, mil, based, woman, learned, stacked, generic, mtt, bounding, large, pose, train, hidden, dae, adapt, multiple, dataset, activation, surfer, animal, target, performance, average, knowledge] [network, existing, size, local] [robust, comparison, sparse, method, key, overcomplete, gradient, number] [particle, data, track, auxiliary, time, process, figure] [set, problem, machine, denote, case] [neural, frame, ieee, appearance, moving, illumination, encoder, learns]
Bayesian Estimation of Latently-grouped Parameters in Undirected Graphical Models
Jie Liu, David Page
Jie Liu, David Page
[algorithm, state, difference, current, apply] [training, test, performance, second, large, propose, evaluate, learned] [beta, group, update, variable, generate, size, structure, move] [number, oracle, random, error, small] [gibbs, bayesian, likelihood, sampling, sample, sba, markov, mle, posterior, grouping, parameter, estimate, chain, figure, distribution, auxiliary, exact, data, log, draw, pcd, process, stripped, dirichlet, intractable, estimation, three, prior, latent, mrfs, proposal, contrastive, testing, time, yielded, auxvar, model, indicates, gaussian, probability, remove, extended, monte, carlo, nonparametric, voting, mixture] [set, estimator, approximation, ratio, mrf, function, maximum, suppose, consider] [inferred, potential, session]
Beyond Pairwise: Provably Fast Algorithms for Approximate $k$-Way Similarity Search
Anshumali Shrivastava, Ping Li
Anshumali Shrivastava, Ping Li
[space, algorithm, natural, choice, sensitive, sum, total, interesting] [similarity, google, based, work, top, report, word, vector, quality, computer, traditional, demonstrate, consists, table, improving] [search, neighbor, binary, pair, science, nearest] [resemblance, hash, pairwise, hashing, minwise, ping, lsh, random, sparse, fast, bucket, retrieved, create, naturally, exist, standard, permutation, provable, existence, retrieve, running, analysis, bucketing] [log, data, time, probability, family, independent, approximate, element, three, sample] [query, theorem, set, problem, proof, case, function, note, paper, point, interested, consistent, approximation, complexity] [retrieval, collision]
Unsupervised Spectral Learning of Finite State Transducers
Raphael Bailly, Xavier Carreras, Ariadna Quattoni
Raphael Bailly, Xavier Carreras, Ariadna Quattoni
[algorithm, observable, computes, sum, state, setting, natural] [learning, unsupervised, input, output, target, hidden, supervised, mapping, performance, work, directly, based, vector] [computed, pair, size, compute, inference, built, empty, synthetic] [matrix, rank, spectral, method, optimization, nuclear, convex, norm, objective, agrees, order] [model, distribution, probability, sample, observation, derived, observed, computational, form, generated, markov, parameter] [hankel, fst, set, generalized, aligned, proposition, problem, minimization, main, relaxation, example, denote, consider, access, paper, linear, unaligned, proof, idea, exists, general, grammatical, theoretical, balle, result, satisfying, solution] [alignment, subject, corresponding, presented]
A New Convex Relaxation for Tensor Completion
Bernardino Romera-Paredes, Massimiliano Pontil
Bernardino Romera-Paredes, Massimiliano Pontil
[appendix, choose, bound, step, algorithm, conference, sampled, school] [learning, vector, average, based, approach, video, dataset, computer, propose, randomly, test, validation, second, experiment, composed] [associated, compute, synthetic, real, computation] [tensor, norm, convex, trace, method, proposed, regularization, matrix, completion, rank, spectral, proximity, order, operator, euclidean, solve, alternating, london, matricization, direction, argmin, singular, conducted, error, numerical, running, decomposition, admm] [describe, equation, figure, remaining, time, university, observation, estimation, alternative, processing] [set, regularizer, relaxation, function, problem, lemma, subgradient, lower, machine, linear, note, procedure, ratio, cardinality, min, gauge, case, tight, prox, minimization, consider] [envelope, property, study, described]
Efficient Algorithm for Privately Releasing Smooth Queries
Ziteng Wang, Kai Fan, Jiaqi Zhang, Liwei Wang
Ziteng Wang, Kai Fan, Jiaqi Zhang, Liwei Wang
[algorithm, upper, bounded, bound, partial, school] [accuracy, class, evaluation, based, learning, vector, table] [degree, compute, variable, size, computation, larger] [running, order, small, basis, sparse, key, supplementary, low, error, numerical] [data, time, respect, approximate, university, kernel] [mechanism, query, trigonometric, private, linear, smooth, approximation, polynomial, answer, summary, set, differentially, answering, theorem, differential, privacy, database, function, constant, laplace, outputting, universe, lemma, machine, smoothness, consider, proof, statistical, peking, laboratory, result, releasing, case, sanitizer, note, generalized, problem, procedure, moe, theory, privately] [study, combination, change, depends, user, noise]
Synthesizing Robust Plans under Incomplete Domain Models
Tuan A. Nguyen, Subbarao Kambhampati, Minh Do
Tuan A. Nguyen, Subbarao Kambhampati, Minh Do
[plan, action, robustness, planning, incomplete, complete, incompleteness, state, realized, add, goal, precondition, belief, schema, conformant, satellite, decision, assume, synthesizing, conference, hhedii, execution, delete, applicable, logistics, synthesize, gripper, ppre, modeled, sequence, wpre, initial, partial, focus, wdel, assessment, successful, qadd, succeeds, fail] [domain, work, knowledge, type, amount, representing, level, hidden, approach] [probabilistic, candidate, real, increasing, generate, semantics, compilation, weighted] [robust, additional, number, stochastic, realization] [model, probability, generating, conditional, time, figure, transition, markov] [problem, set, notion, cost, solution, formulation, condition, note, point] [desired, temporal]
Efficient Exploration and Value Function Generalization in Deterministic Systems
Zheng Wen, Benjamin Van Roy
Zheng Wen, Benjamin Van Roy
[reinforcement, ocp, state, algorithm, action, regret, optimal, episode, bound, apply, space, eluder, period, optimistic, sequence, reward, exploration, deterministic, special, online, interesting, finite, span, upper, agent, policy, benjamin, computationally, rasa, tabula, deliver, previous, horizon, selects, aforementioned] [learning, class, performance, based, applied, generalization, work, knowledge, learn] [disjoint, propagation, michael, van] [number, quadratic, practical] [time, prior, sample, computational, model, observed, positive] [hypothesis, linear, function, complexity, note, theorem, corollary, set, agnostic, consider, proposition, establish, result, general, dimension, loss, case, machine, indicator, problem, depend, cost, polytope, polynomial, proof, design, effective] [constraint, system, presented]
Variance Reduction for Stochastic Gradient Optimization
Chong Wang, Xi Chen, Alex Smola, Eric Xing
Chong Wang, Xi Chen, Alex Smola, Eric Xing
[algorithm, optimal, sampled, natural, bound, explore] [learning, training, better, large, approach, entire, vector, improve, test, international, performance, evaluate] [inference, construct, computed, size, local, reduce, compute] [gradient, stochastic, variance, noisy, reduction, random, convex, convergence, rate, standard, number, optimization, matrix, objective, faster, direction, true, performs, leading, coordinate, ascent] [variational, data, variate, topic, dirichlet, expectation, estimate, latent, document, figure, log, form, distribution, positive, likelihood, corpus, predictive, estimation, respect, allocation, indicates, three, lda] [logistic, lower, function, machine, constant, approximation, set, regression, general, map] [control, term, depends, correlation, estimated, highly, neural]
Sparse Additive Text Models with Low Rank Background
Lei Shi
Lei Shi
[algorithm, sum, bound, choose, assumption, scenario] [supervised, unsupervised, generative, class, large, based, vector, learning, training, accuracy, compared, better, text, table, test] [inference, update, discovering, political, adding] [sparse, low, rank, quadratic, optimization, gradient, constrained, robust, norm, performs, proposed, sparsity, majorization, lagrangian, number, nuclear, computing, accelerated, alternating, updated, updating, direction] [model, topic, background, sage, additive, latent, variational, data, document, multifaceted, modeling, distribution, llb, double, dirichlet, three, bayesian, lda, log, employing, figure, hlog, estimation, approximate, form] [proximal, label, paper, technical, cost, deviation] [term, equality, constraint]
Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions
Tamir Hazan, Subhransu Maji, Joseph Keshet, Tommi Jaakkola
Tamir Hazan, Subhransu Maji, Joseph Keshet, Tommi Jaakkola
[bound, multiplicative, focus, optimal, integer] [learning, prediction, training, approach, learn, learned, image, svm, segmentation, generalization, work, well] [randomized, inference, computed, local, real, graph] [gradient, random, nonnegative, stochastic, constrained, convex, method, regularization] [posterior, distribution, probability, gaussian, bayesian, model, approximate, sampling, log, describe, computational, moment, prior, sample, equation, discrete, tion, processing, gamma, parameter] [map, loss, function, risk, linear, smooth, structured, set, program, theorem, empirical, density, consider, maximum, supermodular, proof, grabcut, minimization, solution, extreme, provide, max, arg, unbiased, machine] [potential, complex, described, term, neural, change]
Heterogeneous-Neighborhood-based Multi-Task Local Learning Algorithms
Yu Zhang
Yu Zhang
[algorithm, step, conference, decision, setting, optimal] [learning, task, wij, wii, based, wik, training, vector, performance, wqr, contribution, table, formulated, ith, propose, jth, cik, test, prediction, cvx, eik, learn, compare, feature, better, british] [local, nearest, neighborhood, heterogeneous, construct, knn, global, update, structure, toy] [method, proposed, solve, objective, optimization, descent, coordinate, number, square, row, denotes, matrix, running, wiaj, record] [data, kernel, figure, element, estimation, time, positive, processing, respect] [problem, function, regression, set, min, machine, point, loss, solution, linear, complexity, solver, hinge, implies, homogeneous, support, violating] [corresponding, neural]
Speedup Matrix Completion with Side Information: Application to Multi-Label Learning
Miao Xu, Rong Jin, Zhi-Hua Zhou
Miao Xu, Rong Jin, Zhi-Hua Zhou
[algorithm, incomplete, assumption, provided, complete, assume, computationally] [learning, based, approach, target, large, feature, training, image, performance, average, flickr, table, vector, prediction] [size, perfectly, developed, missing, reduce, explicitly] [matrix, completion, maxide, number, proposed, optimization, alm, method, recovery, rank, singular, high, standard, recover, subspace, collaborative, norm, error, recovering, factorization, convex, column, trace, application, fpca, objective] [observed, data, time, sample, perfect, computational, tion] [label, transductive, problem, set, result, theory, max, complexity, linear, theoretical, main, guarantee] [side, relative, ieee]
Stochastic Majorization-Minimization Algorithms for Large-Scale Optimization
Julien Mairal
Julien Mairal
[algorithm, online, expected, assume, programming, bounded, optimal, introduce, sequence, choose, assumption, horizon] [dataset, training, learning, approach, dictionary, large, consists, work, propose, class, based, literature] [update, size, weighted, computed, computation] [stochastic, convex, convergence, gradient, scheme, liblinear, optimization, sparse, smm, objective, method, analysis, rate, regularization, averaging, matrix, solving, webspam, factorization, descent, principle, regularized, uniformly] [data, figure, stationary, approximate] [surrogate, function, batch, proximal, proposition, set, minimizing, structured, min, point, classical, note, consider, converges, arg, cost, loss, constant, empirical, machine, case, minimization, solution] [study, signal, constraint, presented]
Sinkhorn Distances: Lightspeed Computation of Optimal Transportation
Marco Cuturi
Marco Cuturi
[optimal, algorithm, space, simplex, fact, sum, total] [metric, well, vector, mnist, large, negative, original, better, propose, image] [scaling, computed, network, computation, perform, compute] [transport, distance, matrix, sinkhorn, pij, number, divergence, classic, computing, regularization, gpu, earth, emd, euclidean, pijqjk, qjk, iteration, regularized, entropic, rct, random, small, mij, cpu, convergence, argmin] [entropy, joint, figure, probability, kernel, computational, log, independence, positive, equation, time, form, mutual, family] [problem, set, point, cost, proof, lemma, theory, consider, linear, theorem, prove, provide, dimension, inequality, subset, extreme] [single, property, speed, varying]
Sparse Inverse Covariance Estimation with Calibration
Tuo Zhao, Han Liu
Tuo Zhao, Han Liu
[assume, competing, achieves] [outperforms, performance, large, vector, representation, propose, training, learning, table, evaluate, roc, good, approach] [graphical, existing, graph] [matrix, epic, precision, covariance, method, sparse, regularization, proposed, elliptical, clime, argmin, cai, adopt, remark, tau, transformed, convergence, spectral, numerical, column, stochastic, norm, summarizes, high, unknown, symmetric, semiparametric, mcc] [estimation, positive, parameter, log, gaussian, estimate, ratetrue, maxj, journal, distribution, multivariate, sample, data, model, inverse, three, independent, chain, figure, selected, university, adopted, breast, testing] [estimator, set, max, linear, program, machine, statistical, pcr, selection, consider, estimating, asymptotically, calibrated] [correlation, tuning, estimated, constraint, sensitivity]
BIG & QUIC: Sparse Inverse Covariance Estimation for a Million Variables
Cho-Jui Hsieh, Matyas A. Sustik, Inderjit Dhillon, Pradeep Ravikumar, Russell Poldrack
Cho-Jui Hsieh, Matyas A. Sustik, Inderjit Dhillon, Pradeep Ravikumar, Russell Poldrack
[algorithm, step, free, appendix, assume, bottleneck] [achieve, based, dataset, large, approach, scale] [compute, update, computed, computation, graph, clustering, size, degree, cache] [number, bigquic, coordinate, sparse, matrix, method, quic, covariance, block, descent, convergence, newton, hessian, key, dimensional, solve, proposed, analysis, store, quadratic, dij, solving, gradient, random, high, computing, xij, speedup, direction, order, scheme, require, nonzeros, optimization, comparison, requires] [time, inverse, figure, positive, data, gaussian, boundary, computational, sample, log, chain, full] [set, complexity, linear, procedure, theorem, machine, note, problem, statistical, lemma, converges, point, solution, cost] [memory, fmri, single, control, stored, plausible]
Compete to Compute
Rupesh K. Srivastava, Jonathan Masci, Sohrob Kazerounian, Faustino Gomez, Jürgen Schmidhuber
Rupesh K. Srivastava, Jonathan Masci, Sohrob Kazerounian, Faustino Gomez, Jürgen Schmidhuber
[best, long] [lwta, relu, learning, training, input, layer, activation, trained, dataset, subnetworks, common, dropout, output, convolutional, negative, test, table, catastrophic, mnist, competitive, recognition, deep, digit, unsupervised, sigmoid, consists, vector, feature, softmax, architecture, cnn, compared, technique, applied, maxout, yoshua, classify, weight, sentiment, performance, multiple] [network, local, size, role] [number, error, block, fraction, rate, analysis] [positive, data, three, computational, university, volume, full, figure] [active, linear, set, machine, john] [neural, wta, biological, pattern, winning, neuron, competition, consisting, sigmoidal, signal, brain, encoding]
Gaussian Process Conditional Copulas with Applications to Financial Time Series
José Miguel Hernández-Lobato, James R. Lloyd, Daniel Hernández-Lobato
José Miguel Hernández-Lobato, James R. Lloyd, Daniel Hernández-Lobato
[best, conference, arbitrary, satisfy] [table, large, prediction, based, compared, international, work, performed, performance, multiple, test, evaluated, approach] [conditioning, synthetic, inference, factor] [method, covariance, proposed, matrix, standard, analysis, asymmetric, typically] [copula, time, model, gaussian, data, conditional, estimation, multivariate, figure, series, distribution, process, three, bayesian, predictive, estimate, bivariate, sjc, marginal, respect, hmm, parametric, univariate, garch, parameter, tvc, journal, approximate, generated, include, dsjcc, cdf, approximates, chf, currency, probability, equity, expectation, clayton, joe] [framework, generalized, density, function, approximation, machine, maximum, approximated] [dynamic, correlation, static]
Streaming Variational Bayes
Tamara Broderick, Nicholas Boyd, Andre Wibisono, Ashia C. Wilson, Michael Jordan
Tamara Broderick, Nicholas Boyd, Andre Wibisono, Ashia C. Wilson, Michael Jordan
[algorithm, step, online, setting, total, chosen, return, initialize] [performance, learning, multiple, table, generative] [size, inference, asynchronous, update, global, local, distributed, processed, worker, computation, collection, thread] [number, streaming, stochastic, true, gradient, descent] [posterior, data, svi, variational, minibatch, bayesian, approximate, time, dirichlet, wikipedia, exponential, bayes, lda, parameter, document, full, prior, family, topic, latent, predictive, log, distribution, model, estimate, probability, expectation, ssu, equal, collect, processing, revisit, hyperparameters, normalizing, tion] [set, approximation, framework, consider, constant, case, batch, machine, note, suppose, approximating] [nature, calculate, master, sensitivity, single]
On Poisson Graphical Models
Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Zhandong Liu
Eunho Yang, Pradeep Ravikumar, Genevera I. Allen, Zhandong Liu
[natural, exp, upper] [negative, approach, original, domain, learning, large, work, learned] [graphical, network, graph, variable, structure, truncation, mass, neighborhood, undirected] [random, pairwise, quadratic, method, pgm, arxiv, preprint, extension, number] [poisson, distribution, model, positive, data, tpgm, joint, multivariate, count, spgm, base, gaussian, univariate, exponential, measure, modeling, conditional, winsorized, truncated, cancer, normalizability, log, major, probability, breast, family, parameter, ratetrue, sequencing, generated, figure, estimation, qpgm, journal, tion, university] [function, consider, proposition, suppose, theorem, consistent, selection, construction, set, constant, linear, close, note, general, paper, statistical] [novel, spatial]
Perfect Associative Learning with Spike-Timing-Dependent Plasticity
Christian Albers, Maren Westkott, Klaus Pawelzik
Christian Albers, Maren Westkott, Klaus Pawelzik
[robustness, current] [learning, input, window, performance, supervised, weight, approach, learn, margin, output] [network, computation] [trace, order, denotes, fraction, error, proposed] [time, perfect] [mechanism, teacher, theoretical, case, function, equivalence, argument, note] [spike, postsynaptic, plasticity, synaptic, neuron, potential, rule, presynaptic, perceptron, membrane, tempotron, stdp, pattern, threshold, desired, associative, spiking, chronotron, neural, ust, rstdp, activity, presented, subthreshold, hyperpolarization, presentation, cstdp, inhibitory, plr, uthr, dependent, heaviside, depends, capacity, biologically, ensures, neuronal, memory, potentiation, excitatory, highly, uad, respective, temporal, combination, synapse, realistic, crossing, timing, load, signal]
Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections
Matthew Lawlor, Steven W. Zucker
Matthew Lawlor, Steven W. Zucker
[natural, space, fact] [embedding, image, visual, randomly, well, dense, vector, perceptual, embeddings, rotating, based, vision] [edge, structure, diffusion, embedded, triple, center, color, van, corresponds, cluster, probabilistic, pair, local, represent] [pairwise, spectral, high, distance, random, oriented, analysis, order, low, imply] [probability, figure, association, joint, conditioned, journal, distribution, independent, conditional, estimate, centered] [statistical, map, note, denote, geometric, hypothesis, provide] [orientation, horizontal, neural, excitatory, xrk, xrj, elder, threshold, explain, scene, relative, xri, texture, cortical, biological, colored, absence, organization, receptive]
DESPOT: Online POMDP Planning with Regularization
Adhiraj Somani, Nan Ye, David Hsu, Wee Sun Lee
Adhiraj Somani, Nan Ye, David Hsu, Wee Sun Lee
[policy, belief, despot, planning, action, online, sampled, upper, agent, state, pomdp, bound, algorithm, initial, default, anytime, uncertainty, current, optimal, pomcp, observable, discounted, reward, pomdps, scenario, programming, height, utility, apply, return, space, best, maximizing, execution, deterministic, executes] [large, performance, good, tag, average, second, table, better, well, compared, work] [tree, search, node, size, root, path, partially, perform, leaf, subtree, heuristic, represent, represents] [number, regularized, distance, small, random, standard] [observation, particle, time, probability, derived, sampling, approximate] [set, lower, maximum, theorem, main, approximation, provide, machine] [dynamic, estimated, described]
On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations
Tamir Hazan, Subhransu Maji, Tommi Jaakkola
Tamir Hazan, Subhransu Maji, Tommi Jaakkola
[bound, algorithm, belief, upper, sampled, assume, expected] [based, approach, work, average, well, prediction] [partition, local, graphical, graph, assignment, inference, propagation, generate, computed, tree, compute] [random, error, dimensional, low, high] [gibbs, distribution, sampling, probability, approximate, sample, model, log, figure, boundary, independent, sampler, describe, computational, discrete, full, marginal, tion, variational, extended, processing, exponential, markov] [map, lower, function, max, theorem, unbiased, gumbel, spin, lemma, complexity, procedure, structured, probable, machine, energy, perturbation, maximum, result, corollary, maximization, provide, theory, set, problem, consider, separation, extreme] [potential, single, glass, attractive, coupling]
Blind Calibration in Compressed Sensing using Message Passing Algorithms
Christophe Schulke, Francesco Caltagirone, Florent Krzakala, Lenka Zdeborova
Christophe Schulke, Francesco Caltagirone, Florent Krzakala, Lenka Zdeborova
[algorithm, transfer, bound, setting, diagram, computationally, belief] [reconstruction, based, work, large, approach, well, paris, performance, supervised] [message, passing, product, sensor, size, factor, larger] [calibration, phase, compressed, distortion, number, measurement, amp, convex, sparse, small, unknown, variance, numerical, order, matrix, cnrs, random, rate, plotted, france, dxil, msecorr, error] [transition, distribution, gaussian, approximate, probability, considered, exact, estimate, figure, indicates, parameter, measure, counting, perfect] [function, problem, case, linear, theory, note, consider, close, general, empirical, paper, lower] [signal, blind, sensing, ieee, noise, study, system, region, hardware]
Solving inverse problem of Markov chain with partial observations
Tetsuro Morimura, Takayuki Osogami, Tsuyoshi Ide
Tetsuro Morimura, Takayuki Osogami, Tsuyoshi Ide
[state, initial, limited, natural, assumption, conference, space, assume, partial, aaai, reinforcement, called] [based, metric, vector, learning, task, prediction, represented, approach] [link, network, corresponds, social] [number, method, matrix, gradient, hitting, rate, proposed, objective, analysis, small, ordinary, denotes, standard, error] [markov, chain, log, inverse, probability, transition, observation, stationary, road, parameter, model, respect, volume, data, riemannian, distribution, figure, lkl, analyzing, monitoring, including, equal, independent, include, positive, sample, observed, visiting, reaching, nwkr] [problem, function, cost, squared, note, set, ibm, paper, derive] [term, infer, estimated, formulate, frequency]
Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation
Vibhav Vineet, Carsten Rother, Philip Torr
Vibhav Vineet, Carsten Rother, Philip Torr
[algorithm, strategy, follow, provided] [object, image, approach, segmentation, based, accuracy, dataset, better, jointly, class, recognition, quality, input, output, pixel] [depth, improvement, inference, unary, kinect] [order, solving, optimization, dual, recovering, decomposition, gradient, pairwise, method] [model, joint, estimation, form, extended, discrete, estimate, distribution, mixture, prior] [problem, energy, estimating, set, cost, provide, consistency, minimization, function, solution, framework, subset] [attribute, intrinsic, illumination, ieee, scene, term, higher, shading, pascal, qualitative, nyu, sirfs, material, ahcrf, dependent, quantitative, shape, single, enforce, barron, anyu, labelling, torr, master, apascal, malik, densecrf, coding]
Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors
Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma
Xiaoqin Zhang, Di Wang, Zhengyuan Zhou, Yi Ma
[lagrange, introduce, previous, apply, conference, sum] [work, image, based, corrupted, represented, applied, original, visual, reconstruction, computer, well, transformation, video, multiple] [structure, synthetic, product] [tensor, rank, unfolding, matrix, method, optimization, rasl, recovery, tensorial, decomposition, norm, number, error, proposed, alternating, tucker, mode, nuclear, direction, convex, column, convergence, tilt, algebra, gradient, small, multiplier, recover, solve, sparse, adopt, completion, analysis, fraction, parafac] [data, three, augmented, figure, form] [problem, set, function, arg, proximal, denote, relax, min, result, general, minimization] [alignment, simultaneously, term, spatial, pattern, equality, viewed, range, highly]
Pass-efficient unsupervised feature selection
Crystal Maung, Haim Schweitzer
Crystal Maung, Haim Schweitzer
[algorithm, step, observe, selects, integer, worst, dominated, maintains] [feature, unsupervised, datasets, computer, improved, input, entire, top, accuracy, based, work] [list, randomized, compute, size, factor, candidate, smaller, appears, symposium] [number, pass, matrix, qrp, iqrp, largest, heap, leverage, implementation, householder, error, requires, small, column, businger, orthogonalization, reduction, create, golub, slower, method, pivoted] [figure, data, time, selected, describe, sampling, accurate, volume, probability, approximate, university] [selection, max, set, linear, arg, approximation, cost, complexity, case, classical, main, subset, approximating, select] [memory, typical, combination]
Learning Trajectory Preferences for Manipulators via Iterative Improvement
Ashesh Jain, Brian Wojcik, Thorsten Joachims, Ashutosh Saxena
Ashesh Jain, Brian Wojcik, Thorsten Joachims, Ashutosh Saxena
[algorithm, optimal, environment, arm, online, regret, goal, space, step, planning, previous, autonomous] [learning, object, learn, scoring, score, average, good, training, context, task, vector, feature, top, table, evaluate, train, better, performance, approach, well, prediction, compare, quality, improve] [move, compute] [distance, high, minimum] [figure, interaction, three, time, sampling, model, describe] [function, set, provide, maximum, consider, note, problem] [trajectory, user, robot, feedback, tpp, human, robotic, study, grocery, ing, motion, checkout, surrounding, manipulation, vertical, moving, preference, waypoints, ranked, mmp, dof, bad, untrained, orientation, capture, waypoint, baxter, manipulated, fragile]
Summary Statistics for Partitionings and Feature Allocations
Isik B. Fidaner, Taylan Cemgil
Isik B. Fidaner, Taylan Cemgil
[cumulative, expected, algorithm, sequence, sum, apply] [feature, based, dataset, approach, appear, segmentation, extract, well, compare] [size, represent, weighted, clustering, tree, develop, synthetic, path] [block, pairwise, number, projection, matrix, permutation, incremental, minimum, random, written] [entropy, mixture, partitioning, sample, log, figure, distribution, agglomeration, three, bayesian, statistic, posterior, data, cod, gene, process, respect, occurence, quantify, summarize, dirichlet, probability, occurences, crp, journal, dendrogram, bioinformatics, nonparametric, sampling, inserting, form, component, prior, galactose, multiset, element] [set, subset, problem, maximum, general, example, function, solution] [segment, single, young]
What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach
Zhenwen Dai, Georgios Exarchakis, Jörg Lücke
Zhenwen Dai, Georgios Exarchakis, Jörg Lücke
[natural, chosen, algorithm] [image, feature, mask, invariant, learning, visual, generative, globular, learned, convolutional, hidden, occlusive, explicit, object, patch, temperature, translation, gabor, approach, decreased, pixel, based, applied, emerge, generation, exclusiveness] [probabilistic, variable, inference, associated, depth, occurrence, van] [high, row, sparse, numerical, regularization] [model, component, data, distribution, posterior, parameter, prior, generated, gaussian, computational, exact, selected] [linear, set, approximation, studied, cost, map] [position, encoding, neural, receptive, estimated, complex, scalar, study, simple, infer, noise, presence, supplement, stimulus, encode, capture, earlier, typical]
Actor-Critic Algorithms for Risk-Sensitive MDPs
Prashanth L.A., Mohammad Ghavamzadeh
Prashanth L.A., Mohammad Ghavamzadeh
[policy, reward, discounted, state, appendix, algorithm, critic, spsa, decision, simultaneous, return, actor, setting, action, prashanth, mdps, sum, optimal, lagrange, observe, employ, initial, bellman, advantage, reinforcement, conference, expected, maximizing] [average, based, performance, vector, learning, work, automatic, well] [update, pair] [gradient, stochastic, square, variance, random, proposed, convergence, optimization, lagrangian, standard, objective] [estimate, measure, markov, parameter, distribution, time, figure, independent, log] [function, risk, perturbation, approximation, note, consider, lemma, differential, point, cost, derive, set, formulation, machine, max, result, procedure] [control, variability, signal, ieee, calculate, system]
Firing rate predictions in optimal balanced networks
David G. Barrett, Sophie Denève, Christian K. Machens
David G. Barrett, Sophie Denève, Christian K. Machens
[optimal, programming, identify] [prediction, representation, relationship, input, large, bottom, negative, variety, technique] [network, balance, represent, computation, represents, allows] [rate, error, quadratic, matrix, standard] [equation, positive, computational, measure, journal, figure, model] [function, linear, loss, cost, optimisation, solution, theoretical, theory, active, condition, algorithmic] [tuning, neuron, neural, signal, spiking, balanced, connectivity, spike, curve, tightly, activity, noise, potential, excitation, membrane, calculate, system, individual, inhibition, neuroscience, eye, temporal, left, calculating, interpret, produce, inhomogeneity, population, region, produced, machens, coding, term, inhomogeneous, silent, response, threshold, regularly, closely, inhibitory, middle, recurrent, monotonic, cortical]
Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
John Duchi, Martin J. Wainwright, Michael Jordan
John Duchi, Martin J. Wainwright, Michael Jordan
[minimax, optimal, bound, space, strategy, setting, focus, chosen] [vector, based, work, class, achieve, second, better] [local, randomized, collection, american, inference, size] [rate, convergence, basis, standard, random, error, projection, uniformly, orthogonal, proposed] [estimation, probability, data, multinomial, sample, histogram, journal, sampling, distribution, nonparametric, estimate, testing, series, log, drawn, locally] [privacy, statistical, private, density, lower, differential, denote, estimator, problem, classical, consider, set, function, providing, risk, provide, proposition, main, theory, constant, attain, paper, orthonormal, perturbation, result, differentially, disclosure, sobolev, survey, theoretical, lipschitz, answer, framework, smoothness, warner, turn, mechanism, procedure] [sharp, study, response, noise, population, channel]
Bayesian inference for low rank spatiotemporal neural receptive fields
Mijung Park, Jonathan Pillow
Mijung Park, Jonathan Pillow
[algorithm, space, maximizing, highest] [test, training, lnp, average, prediction, achieved, vector, based, visual, well] [evidence, inference, develop, computation, perform, structure] [matrix, rank, method, covariance, number, fast, error, row, separable, dimensional, low] [conditional, posterior, gaussian, likelihood, approximate, model, prior, bayesian, sampling, data, sample, estimate, form, poisson, ald, sta, full, hyperparameters, distribution, normal, journal, log, marginal, figure, time, generated] [linear, regression, set, closed, max, estimating, arg, denote] [temporal, spatial, receptive, neural, stimulus, simple, localized, noise, response, encoding, relative, fully, simulated, spatiotemporal, described, novel, neuron, reduced, integration]
Buy-in-Bulk Active Learning
Liu Yang, Jaime Carbonell
Liu Yang, Jaime Carbonell
[total, bound, algorithm, space, sequential, return, conference, advantage, round, sum] [learning, large, based, labeled, international, multiple] [size, update, factor, communication, smaller, larger, delay] [number, cal, robust, analysis, method, mode, expect, required, rate, error, random, small] [probability, log, distribution, time, analogous, sample, model] [active, cost, label, complexity, batch, request, realizable, function, machine, passive, case, tsybakov, denote, sublinear, note, theorem, interested, implies, consider, ibm, dxy, budget, suppose, max, set, result, constant, condition, version, guarantee, union, studied, letting, annals, risk, theoretical, stated] [noise, study, loop]
Sensor Selection in High-Dimensional Gaussian Trees with Nuisances
Daniel S. Levine, Jonathan P. How
Daniel S. Levine, Jonathan P. How
[greedy, bound, algorithm, belief, optimal, policy, uncertainty] [performance, learning, output] [focused, graphical, graph, nonlocal, inference, unique, path, relevant, unfocused, computed, node, sensor, vectoral, message, local, conditioning, distributed, passing, edge, gabp, propagation, gmrf, runtime, subgraph, compute, schur, thin, induced, disjoint, nuisance, associated, separate] [random, pairwise, precision, matrix, decomposition, computing] [gaussian, latent, conditional, chain, markov, figure, mutual, distribution, conditioned, multivariate, independent, computational, log, independence, joint, model, marginal] [problem, set, selection, subset, active, consider, proposition, example, cost, selector, adjacent, max, complexity, paper] [scalar, rule]
Sequential Transfer in Multi-armed Bandit with Finite Set of Models
Mohammad Gheshlaghi azar, Alessandro Lazaric, Emma Brunskill
Mohammad Gheshlaghi azar, Alessandro Lazaric, Emma Brunskill
[regret, arm, transfer, tucb, mucb, bandit, optimal, umucb, ucb, algorithm, optimistic, episode, rtp, bound, online, assumption, previous, pulled, current, sequential, reinforcement, worse, learner, azar, uncertainty, cumulative, conference, introduce, anandkumar, computes, best, pull, setting, focus] [learning, performance, knowledge, approach, task, report, improve, second, transferring, illustrated] [compute, third] [number, tensor, matrix, gap, method, error, small, remark, unknown, objective, largest] [model, prior, figure, estimate, distribution, three, drawn, sample, log, observed, power] [set, problem, theorem, complexity, paper, result, prove, derive, framework, min, consider] [estimated, actual, corresponding]
Sparse Overlapping Sets Lasso for Multitask Learning and its Application to fMRI Analysis
Nikhil Rao, Christopher Cox, Rob Nowak, Timothy T. Rogers
Nikhil Rao, Christopher Cox, Rob Nowak, Timothy T. Rogers
[bound, assume, optimal, upper, conference] [task, vector, learning, similarity, feature] [group, size, variable] [sparse, sparsity, error, norm, optimization, subspace, dual, method, gradient, standard, random, arxiv, analysis, preprint, convex, matrix] [data, figure, selected, parameter, respect, restricted] [lasso, soslasso, loss, function, set, consider, glasso, regression, lemma, multitask, max, consistency, regularizer, maximum, solution, active, proof, logistic, suppose, support, derive, squared, note, paper, result, problem, general, anatomical, decomposable, example, theorem, linear, constant, exists, arg] [voxels, overlapping, fmri, brain, indicate, varying, activity, relative, corresponding]
Reconciling priors'' & "priors" without prejudice?
Remi Gribonval, Pierre Machart
Remi Gribonval, Pierre Machart
[optimal, focus, choice, inria, interesting, arbitrary, called, fact] [denoising, approach, context, explicit] [unique, global, associated, evidence, existing] [convex, optimization, argmin, separable, minimum, matrix, regularization, quadratic, order, descent, coordinate, sparse] [gaussian, inverse, bayesian, log, prior, distribution, stationary, additive, estimate, white, estimation, drawn, conditional, computational, referred, observation, probability] [mmse, problem, result, function, estimator, linear, main, lemma, theorem, set, expressed, penalty, point, corollary, solution, exists, regression, loss, regularizer, provide, machine, invertible, paper, multiplicatively, case, additively, regularizers, generalize, convexity, penalized, map, squared, relate, clear] [minimizer, noise, signal, simple, term, decoder, rise, light]
Correlated random features for fast semi-supervised learning
Brian McWilliams, David Balduzzi, Joachim Buhmann
Brian McWilliams, David Balduzzi, Joachim Buhmann
[algorithm, assumption, computationally, space, best, step, observe] [performance, labeled, training, learning, large, unlabeled, datasets, prediction, gram, constructing, generalization, outperforms, report, table, introduced, improve, work, randomly, based, improved, avg, kakade, second] [runtime, construct] [sssl, xnv, random, canonical, method, cca, number, error, ridge, fourier, ssslm, analysis, variance, reduction, matrix, penalizing, comparison, icml, argmin, sarcos, norm, cal, standard, smoothed, eigenfunctions] [kernel, data, computational, sampling, accurate, exact, estimate, approximate] [regression, set, approximation, linear, bias, reduces, theoretical, main, empirical, theorem, denote, proposition, shrinkage] [correlation, correlated]
Understanding variable importances in forests of randomized trees
Gilles Louppe, Louis Wehenkel, Antonio Sutera, Pierre Geurts
Gilles Louppe, Louis Wehenkel, Antonio Sutera, Pierre Geurts
[appendix, sum, decision, best, total] [input, learning, large, output, table, work, level, appear, compare, training, building] [variable, randomized, totally, computed, ensemble, impurity, relevant, irrelevant, built, tree, developed, size, masking, node, decrease, mdi, split, forest, root, perfectly, characterization, binary, depth, illustrates, gini, increasing, understanding, conditioning, larger, decomposes, bagging] [random, decomposition, number, analysis] [sample, equation, conditioned, derived, respect, asymptotic, equal, measure, interaction, journal, longer, informative, entropy, figure, mutual, conditional, drawn, selected] [machine, theorem, theoretical, subset, consider, case, set, regression, proposition, example] [fully, single, depends, simple]
Eluder Dimension and the Sample Complexity of Optimistic Exploration
Dan Russo, Benjamin Van Roy
Dan Russo, Benjamin Van Roy
[action, algorithm, regret, bound, thompson, ucb, reward, bandit, eluder, agent, sequence, assume, contextual, conference, optimal, upper, assumption, exploration, expected, optimistic, linearly, space] [class, learning, work, supervised, feature, performance, large, vector, learn, second] [width] [number, random, analysis, stochastic, high, error, true, order] [sampling, time, probability, model, log, process, measure, distribution, independent, prior, respect, dependence] [linear, dimension, function, set, consider, proposition, problem, example, provide, notion, arg, case, complexity, general, generalized, depend, lemma, result, empirical, denote, studied, select, machine, statistical, theory, subset, squared] [depends, study, stronger]
Learning word embeddings efficiently with noise-contrastive estimation
Andriy Mnih, Koray Kavukcuoglu
Andriy Mnih, Koray Kavukcuoglu
[current, natural, best, conference, involves] [word, training, language, context, trained, learning, embeddings, accuracy, approach, learned, ivlbl, target, nce, similarity, vector, representation, large, predict, better, vocabulary, semantic, performance, based, table, sentence, google, challenge, learn, feature, vlbl, traditional, simpler, msr, international, mnih, percentage, syntactic, embedding, well, considerably, gutenberg, predicting, reported, train, scoring] [probabilistic, scalable, size, perform] [method, gradient, rate, computing, proposed, number, adagrad] [model, data, distribution, time, estimation, modelling, likelihood, probability, wikipedia, conditional, inverse] [machine, linear, note, set, result, simply, function] [neural, noise, normalized, simple, single]
Scalable Inference for Logistic-Normal Topic Models
Jianfei Chen, June Zhu, Zi Wang, Xun Zheng, Bo Zhang
Jianfei Chen, June Zhu, Zi Wang, Xun Zheng, Bo Zhang
[algorithm, conference] [training, large, learning, learned, international, layer] [inference, scalable, perplexity, parallel, variable, existing, scalability, develop, graph, local, size, perform, real] [number, method, computing, denotes, deal, fast, order, iteration] [gctm, topic, data, sampling, distribution, gibbs, time, posterior, vctm, bayesian, prior, document, draw, augmentation, model, dirichlet, normal, lda, zdn, multinomial, latent, ctm, sample, sampler, approximate, variational, figure, gaussian, conjugate, conditional, nytimes, auxiliary, process, tsinghua, national, drawn, journal] [set, logistic, complexity, machine, note, denote, empirical] [correlation, dynamic, simple]
Spectral methods for neural characterization using generalized quadratic models
Il M. Park, Evan W. Archer, Nicholas Priebe, Jonathan Pillow
Il M. Park, Evan W. Archer, Nicholas Priebe, Jonathan Pillow
[expected, natural, history, space, special] [prediction, performance, train, feature, multiple, class, based] [computation, inference] [quadratic, spectral, analysis, dimensionality, eigenvectors, projection, matrix, reduction, subspace, covariance, canonical, fast] [gqm, gaussian, model, poisson, mel, distribution, full, nonlinear, estimate, likelihood, retinal, estimation, figure, expectation, journal, computational, axis, replacing, derived, form, modeling, three, ganglion, bayesian, accurate, processing] [linear, generalized, maximum, function, note, general, estimator, provide, framework] [stimulus, neural, spike, noise, glm, response, nonlinearity, depends, term, spiking, potential, gqms, analog, membrane, cmel, volterra, stc, intracellular]
Bayesian Inference and Online Experimental Design for Mapping Neural Microcircuits
Ben Shababo, Brooks Paige, Ari Pakman, Liam Paninski
Ben Shababo, Brooks Paige, Ari Pakman, Liam Paninski
[optimal, algorithm, chosen, online, assume, current, choose, uncertainty] [approach, weight, large, well, mapping, experiment, multiple, based, work, reconstruction] [inference, perform, compute, variable, local, event] [optimization, number, objective, sparse, random, recover, trace, coordinate] [variational, posterior, model, entropy, data, prior, sampling, distribution, full, gibbs, figure, gaussian, time, bayesian, approximate, probability, slab, journal, exact, estimate, likelihood] [design, function, procedure, general, selection, approximation, set, minimizing, statistical] [synaptic, neuron, experimental, trial, neural, postsynaptic, stimulus, connectivity, presynaptic, stimulate, cell, single, stimulating, stimulation, noise, excitatory, corresponding, hardware, identity, response, inhibitory, biological, blue, realistic, needed, dependent]
Reflection methods for user-friendly submodular optimization
Stefanie Jegelka, Francis Bach, Suvrit Sra
Stefanie Jegelka, Francis Bach, Suvrit Sra
[algorithm, best, total, apply, special, sum, optimal] [extremely, class, approach, applied, segmentation, based] [graph, existing, applying, parallel, splitting, iter, computed] [dual, convex, method, solving, optimization, projection, descent, convergence, solve, decomposition, extension, duality, faster, alternating, rate, cut, coordinate, block, computing, orthogonal, iteration, analysis, fast, variation, small, accelerated, gradient, require, typically, key, gap] [discrete, smoothing, figure, log, time, form, journal, continuous, include] [submodular, problem, function, minimization, proximal, set, min, smooth, solution, subgradient, combinatorial, approximation, nonsmooth, minimizing, primal, max, concave, equivalent, consider, sfm, lemma, bcd, solved, converges, easy, formulation, case, main, easily, energy] [corresponding, simple]
Online Learning of Nonparametric Mixture Models via Sequential Variational Approximation
Dahua Lin
Dahua Lin
[algorithm, sequential, online, optimal, introduce] [learning, based, large, image, learn, better, propose, average, vector, conventional, practice, performance, hierarchical, approach] [inference, david, synthetic, dpmm, local, merge, partition, initialization, real, michael, existing, prune] [method, random, proposed, stochastic, number] [posterior, variational, mixture, distribution, dirichlet, bayesian, data, component, nonparametric, model, process, figure, conjugate, sample, approximate, predictive, topic, mcmc, measure, likelihood, sampling, sva, family, wang, parameter, estimate, probability, chong, observed, independent, unnecessary, log, journal, tackle, prior, gaussian, redundant, base, testing, modeling, tractable] [approximation, set, solution, consider, derive, massive] []
Online Robust PCA via Stochastic Optimization
Jiashi Feng, Huan Xu, Shuicheng Yan
Jiashi Feng, Huan Xu, Shuicheng Yan
[online, algorithm, optimal, provided, expected, observe, achieves, singapore, difference] [performance, based, learning, large, corrupted, tracking, demonstrate, work, better, essentially] [global, implemented] [pca, robust, subspace, matrix, sparse, method, optimization, basis, rpca, pcp, proposed, grasta, nuclear, norm, stochastic, solving, principal, factorization, incremental, order, gradient, convergence, standard, number, objective, denotes, rank, analysis, big, convex, recovery, lrt, updating] [sample, data, component, corruption, figure, observed, ambient, computational, time, national, estimation, plot] [function, solution, batch, cost, theorem, converges, problem, denote, prove, dimension, min, surrogate, condition, empirical, guarantee, complexity, minimizing, set, main, loss, proof, linear] [memory, intrinsic, noise]
Latent Maximum Margin Clustering
Guang-Tong Zhou, Tian Lan, Arash Vahdat, Greg Mori
Guang-Tong Zhou, Tian Lan, Arash Vahdat, Greg Mori
[action, algorithm, best, exploit, current, total] [video, margin, tag, mmc, lmmc, learning, svm, unsupervised, trecvid, supervised, vector, med, instance, large, detection, dataset, template, conventional, represented, representation, better, performance, based, score, ucf, work, learn, feature, object, handle, visual, propose, training] [clustering, cluster, variable, yit, assignment, assigned, inference, balance, develop, implement, binary, structural, event] [optimization, method, kth, alternating, standard, descent, solve, proposed, number] [latent, model, data, three, describe, figure, sample] [maximum, framework, set, note, labeling, linear, function, risk, problem] [human, unobserved, constraint, presence, absence, normalized, man]
Stochastic Gradient Riemannian Langevin Dynamics on the Probability Simplex
Sam Patterson, Yee Whye Teh
Sam Patterson, Yee Whye Teh
[online, natural, step, algorithm, simplex, achieves, conference, expected, choice] [performance, learning, large, test, scale, fisher, international] [inference, size, applying, perplexity, update, developed] [gradient, stochastic, small, matrix, method] [langevin, probability, variational, data, dirichlet, riemannian, posterior, equation, prior, topic, latent, document, sampling, bayesian, gibbs, distribution, parameterisation, parameter, rld, monte, carlo, full, mcmc, model, sample, ovb, corpus, proposal, boundary, allocation, figure, log, sgld, wikipedia, three, manifold, form, chain, hsvg, markov, estimate, geometry, correction, investigate, lda, collapsed, sgrld, mixing] [machine, set, effective, approximation, batch, framework] [produced, neural, corresponding]
Wavelets on Graphs via Deep Learning
Raif Rustamov, Leonidas Guibas
Raif Rustamov, Leonidas Guibas
[adaptive, goal, greedy] [level, wavelet, training, haar, reconstruction, predict, learning, deep, quality, class, approach, average, representation, better, temperature, trained, applied, based, constructing, test, learn, vanishing, face] [graph, scaling, lifting, update, underlying, weighted, structure, laplacian, parent, vertex, network, lifted, connected, corresponds, computed] [number, matrix, sparse, scheme, transform, error, sparsity, analysis, spectral, diagonal, order, optimization, largest, eigenvectors] [figure, data, processing, multiscale, process] [construction, approximation, set, problem, active, function, smooth, provide, linear, point, note, consider, machine, paper, constant] [detail, region, signal, neural, corresponding, ieee]
The Power of Asymmetry in Binary Hashing
Behnam Neyshabur, Nati Srebro, Ruslan Salakhutdinov, Yury Makarychev, Payman Yadollahpour
Behnam Neyshabur, Nati Srebro, Ruslan Salakhutdinov, Yury Makarychev, Payman Yadollahpour
[future, arbitrary] [similarity, mapping, short, learning, datasets, semantic, learn, based, training, approach, image, better, average, mnist, represented, work, table, well, evaluate, test, entire] [binary, distinct, allows, bit, communication, optimize] [hash, asymmetric, matrix, distance, hamming, symmetric, hashing, precision, sij, labelme, asymmetry, optimization, shorter, number, euclidean, bitsaverage, additional, store, ksh, precisionbits, allowing, required, row, small, constrained, objective, mlh, fast] [data, length, figure, allow, approximate, parametric, power, computational, considering] [database, function, consider, set, linear, loss, minimal, compact, approximating, query, thresholded, cost, extreme] [code, threshold, single, uniform, coding, actual]
When in Doubt, SWAP: High-Dimensional Sparse Recovery from Correlated Measurements
Divyanshu Vats, Richard Baraniuk
Divyanshu Vats, Richard Baraniuk
[algorithm, greedy, chosen, assume, choose] [performance, level, based, vector, initialized, training] [size, degree, synthetic, perform, real, variable, mar] [swap, sparse, recovery, true, matrix, number, standard, measurement, sparsity, random, rate, accurately, numerical, required, minimum, notation, unknown, tlasso, cosamp, error, eigenvalue, orthogonal, small, iteratively] [figure, estimate, expression, parameter, gene, journal, exact, data, model, computational, accurate, cancer, restricted, sample, log] [support, loss, example, clearly, lasso, theorem, problem, condition, main, annals, linear, active, selection, design, estimating, foba, regression, theoretical, paper, statistical, minimizes] [correlated, correlation, ieee, signal]
Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream
Daniel L. Yamins, Ha Hong, Charles Cadieu, James J. DiCarlo
Daniel L. Yamins, Ha Hong, Charles Cadieu, James J. DiCarlo
[space, step, round] [object, visual, recognition, hierarchical, convolutional, image, representation, task, well, work, category, boosting, performance, measured, class, output, variety, similarity, level, large, achieve, predicted, dissimilarity, input, test] [structure, network, construct] [optimization, high, matrix, number, basic, comparison, error, variation] [model, data, computational, testing, processing, figure, including, estimate] [set, linear, screening, procedure, regression, hypothesis] [neural, ventral, human, hmo, population, nhm, stream, response, stimulus, produce, rdm, brain, individual, institute, neuronal, code, monkey, functional, produced, simple, cortical, rdms, heterogenous, cortex, temporal, described, nrb, neuron, higher, macaque, shape]
An Approximate, Efficient LP Solver for LP Rounding
Srikrishna Sridhar, Stephen Wright, Christopher Re, Ji Liu, Victor Bittorf, Ce Zhang
Srikrishna Sridhar, Stephen Wright, Christopher Re, Ji Liu, Victor Bittorf, Ce Zhang
[algorithm, optimal, oblivious, integer, provided, appendix, programming, step, round, bound] [quality, based, approach, large, award, compare, entity, amazon] [vertex, graph, factor, runtime, parallel, asynchronous, supported, smaller, inference] [scheme, solve, analysis, number, objective, convergence, lagrangian, random, descent, stochastic, dual, gap] [approximate, time, figure, three, augmented, indicates, family] [solution, rounding, approximation, thetis, set, integral, linear, problem, cplex, cover, feasible, theorem, formulation, fractional, comparable, primal, rsol, machine, complexity, combinatorial, program, scd, theory, lmax, nnz, solved, cost, commercial, stephen, main, dblp, covering, minimization, consider, alg, solver, packing] [described, depends]
Action from Still Image Dataset and Inverse Optimal Control to Learn Task Specific Visual Scanpaths
Stefan Mathe, Cristian Sminchisescu
Stefan Mathe, Cristian Sminchisescu
[action, sequential, reward, conference, state, reinforcement, future] [visual, task, recognition, image, context, computer, prediction, learning, large, vision, scale, object, based, dataset, predict, training, learn, average, metric, learned, voc, international, hog, feature, baseline, trained, work, evaluation] [search, center, compute, auc, group] [order, random] [model, data, time, inverse, derived, likelihood, length, three, entropy, measure] [consistency, set, function, map, support, maximum, machine] [human, eye, saliency, aoi, scanpaths, movement, spatial, agreement, aois, gaze, subject, interest, match, control, scanpath, ieee, collected, pattern, alignment, study, eyetracking, correspond, complex, irl]
A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data
Jasper Snoek, Richard Zemel, Ryan P. Adams
Jasper Snoek, Richard Zemel, Ryan P. Adams
[gain, space, modeled] [learned, learn, ability, embedding, learning, validation, visualization, experiment] [scaling, factor] [rate, matrix, pairwise, random, diagonal, analysis, low, high] [model, latent, data, dpp, time, component, process, figure, probability, kernel, poisson, likelihood, dependence, modeling, three, independent, extended, joint, intensity, log, include, equation] [point, linear, consistent, set, empirical, generalized, function, example, provide, machine] [spiking, stimulus, neural, periodic, neuron, spike, inhibitory, determinantal, individual, theta, behavior, pyramidal, inhibition, frequency, glm, capture, single, simulated, interneurons, rhythm, modulation, activity, hippocampus, moving, hippocampal, strong, bar, normalization, csicsvari, learns, corresponding, inhibit, simultaneously, receive, modulates]
Modeling Clutter Perception using Parametric Proto-object Partitioning
Chen-Ping Yu, Wen-Yu Hua, Dimitris Samaras, Greg Zelinsky
Chen-Ping Yu, Wen-Yu Hua, Dimitris Samaras, Greg Zelinsky
[natural, initial, follow, optimal] [image, feature, visual, similarity, object, segmentation, work, based, dataset, vector, truth, computer, approach, level, meaningful, evaluation, detection] [ground, edge, size, search, pair, group, computed, belong, existing, graph] [method, number, distance, emd, rank, order, optimization, gradient, earth, robust] [model, mixture, parameter, journal, partitioning, mle, distribution, data, three, time, parametric, component, figure, measure, estimation, university] [adjacent, set, density, function] [clutter, perception, weibull, human, superpixels, superpixel, correlation, scene, correlated, wmm, normalized, nls, orientation, suggests, segmented, segment, texture, bin]
Learning Feature Selection Dependencies in Multi-task Learning
Daniel Hernández-Lobato, José Miguel Hernández-Lobato
Daniel Hernández-Lobato, José Miguel Hernández-Lobato
[scenario, assumption, algorithm, assume, share, natural] [learning, feature, task, training, average, reconstruction, scale, pixel, introduced, vector, prediction, evaluate, shared] [relevant, irrelevant, inference, factor, propagation, synthetic, structure, evidence, real, update] [matrix, sparse, number, proposed, gradient, error, sparsity, method, regularization, small] [model, data, prior, respect, approximate, horseshoe, distribution, figure, process, estimation, log, latent, gaussian, equal, bayesian, hsdep, posterior, considered, joint, expectation, ssmt, exact, zmt, hsst, observed, journal] [selection, consider, set, machine, linear, denote, cost, problem, regression, constant] [described, corresponding, correlation, correspond]
Cluster Trees on Manifolds
Sivaraman Balakrishnan, Srivatsan Narayanan, Alessandro Rinaldo, Aarti Singh, Larry Wasserman
Sivaraman Balakrishnan, Srivatsan Narayanan, Alessandro Rinaldo, Aarti Singh, Larry Wasserman
[algorithm, bound, assume, chosen, upper, appendix, denoted] [level, class, instance, learning, large, work] [cluster, tree, clustering, connected, mass, supported, graph, collection] [dimensional, number, euclidean, high, convergence, small, distance, low, unknown, noisy, mild, recovering] [sample, manifold, probability, distribution, data, log, figure, geodesic, estimate, journal, full, drawn, estimation, respect, volume, latent, restriction, measure] [density, dasgupta, chaudhuri, rsl, lower, condition, ball, consistency, consistent, lemma, set, radius, point, complexity, estimating, theorem, main, result, construction, linkage, disconnected, inside, paper, machine, case, dimension, analyze, problem, depend, internally, prove, curvature] [noise, single, uniform, connection, clutter, study]
Fantope Projection and Selection: A near-optimal convex relaxation of sparse PCA
Vincent Q. Vu, Juhee Cho, Jing Lei, Karl Rohe
Vincent Q. Vu, Juhee Cho, Jing Lei, Karl Rohe
[optimal, algorithm, minimax, assumption, satisfy, called] [input, work, based, approach, propose, jmlr, class] [global, variable] [principal, matrix, sparse, subspace, analysis, pca, covariance, projection, convex, admm, tau, method, largest, eigenvectors, thresholding, fantope, symmetric, optimization, error, regularization, additional, dspca, rate, rank, spiked, high, fps, solving, standard, wide, sparsity, norm, diagonal, iterative, direction, dual, proposed, alternating] [sample, component, estimation, parameter, distribution, form, university, estimate, simulation] [statistical, theorem, problem, corollary, lemma, theoretical, solution, estimator, relaxation, general, framework, result, provide, penalty, dimension, support, squared, program] [correlation, novel, population, corresponding, nonzero, constraint]
Dimension-Free Exponentiated Gradient
Francesco Orabona
Francesco Orabona
[bound, regret, algorithm, exp, online, dfeg, exponentiated, upper, optimal, sequence, omd, fact, introduce, choice, cumulative, mirror, round, sum, choose] [learning, input, second, vector, dataset, negative, performance, work] [local, global, third, versus] [norm, gradient, convex, analysis, order, dimensional, descent, number, hessian, proposed, supplementary, regularization] [log, kernel, equal, time, figure, derived, family] [lemma, regularizer, theorem, proof, loss, prove, set, function, lower, competitor, smoothness, note, machine, linear, general, inequality, constant, consider, squared, result, case, dimension, differentiable, denote, convexity, access, hold, lipschitz, main] [strong, term, perceptron, depends, range]
Learning invariant representations and applications to face verification
Qianli Liao, Joel Z. Leibo, Tomaso Poggio
Qianli Liao, Joel Z. Leibo, Tomaso Poggio
[conference, unconstrained, natural, best, benchmark, current] [face, recognition, performance, object, invariant, image, computer, template, lfw, transformation, vision, dataset, convolutional, approach, orbit, training, unsupervised, test, international, translation, pooling, feature, pubfig, signature, table, depicting, roc, visual, labeled, representation, dot, second, hog, rotating, learning, task, well] [local] [random, method, order] [model, distribution, figure, background, respect, inner, data] [invariance, set, empirical, theory, consider, case, function, subset, notion, example, paper, statistical, machine, lower] [rotation, ieee, neural, pattern, illumination, brain, ventral, normalized, system, strong, simple, control]
Learning Stochastic Inverses
Andreas Stuhlmüller, Jacob Taylor, Noah Goodman
Andreas Stuhlmüller, Jacob Taylor, Noah Goodman
[algorithm, adaptive, setting, explore, previous, add] [training, learning, learn, train, based, trained, recognition, large, work, temperature, learned] [inference, network, size, node, local, graph, probabilistic, compute, generate, structure, leaf] [number, error, factorization, stochastic, block, convergence, order] [inverse, posterior, mcmc, sampling, bayesian, figure, gibbs, conditional, prior, data, distribution, proposal, approximate, bayes, pah, sampler, acceptance, estimate, observation, conditionals, amortized, pbw, latent, sample, probability, model, allow, interaction, drawn, journal, marginals] [estimator, consistent, set, theorem, density, consider, regression, predictor, empirical, ratio, converges, logistic] [frequency, single, adaptation, estimated, produce, described]
Regression-tree Tuning in a Streaming Setting
Samory Kpotufe, Francesco Orabona
Samory Kpotufe, Francesco Orabona
[space, algorithm, setting, bound, optimal, online, start] [metric, average, training, learning, work] [size, partition, center, assigned, nearest, diameter, neighbor] [phase, error, unknown, streaming, rate, variance, euclidean, incremental, convergence, pick, number, modern, sequentially, analysis, fast] [data, time, distribution, measure, estimate, figure, sample, log, parameter, nonparametric, marginal, probability] [dimension, regression, lemma, problem, nxs, main, point, suppose, proof, set, theorem, maintaining, idea, procedure, closest, denote, prove, exists, result, bias, consider, depend, lipschitz, inequality, arrives, technical, general, query, case, solution, version, machine] [guess, tuning, estimated, institute, control]
Noise-Enhanced Associative Memories
Amin Karbasi, Amir Hesam Salavati, Amin Shokrollahi, Lav R. Varshney
Amin Karbasi, Amir Hesam Salavati, Amin Shokrollahi, Lav R. Varshney
[algorithm, assume, state, fact] [learning, amount, large, vector, performance, average, work, level, weight] [network, cluster, graph, update, improves, node, degree, connected, local, reliably] [error, number, noisy, subspace, running, analysis, fraction, stochastic, iteration, random, proposed] [model, figure, probability, exponential, processing, time, correction, form, observed] [set, note, function, consider, linear, theoretical, proof, provide, bipartite] [noise, internal, pattern, external, neural, associative, memory, correct, recall, constraint, neuron, ser, storage, threshold, noiseless, pci, phenomenon, capacity, ieee, retrieval, brain, stopping, unreliable, subpattern, olfactory, corresponding]
Mapping paradigm ontologies to and from the brain
Yannick Schwartz, Bertrand Thirion, Gael Varoquaux
Yannick Schwartz, Bertrand Thirion, Gael Varoquaux
[strategy] [activation, reverse, forward, approach, learning, large, explicit, visual, face, cross, represented, common, task, validation, work, mapping, training, performance, class, well, rare, test, content, train, challenge, predict, description, better, scale, image] [inference, structure, occurrence, reduce] [number, small, standard, precision] [figure, predictive, model, corpus, data, naive, probability] [map, statistical, logistic, database, provide, set, design, framework, linear] [cognitive, brain, term, functional, stimulus, study, experimental, auditory, fmri, mental, neural, voxels, individual, avoid, cogpo, paradigm, highly, response, imaging, cortex, corresponding, capture, modality, spatial, ontology, presence, recruited]
Robust Spatial Filtering with Beta Divergence
Wojciech Samek, Duncan Blythe, Klaus-Robert Müller, Motoaki Kawanabe
Wojciech Samek, Duncan Blythe, Klaus-Robert Müller, Motoaki Kawanabe
[algorithm, robustness, maximizing, provided, biomedical, step] [common, class, learning, work, performed, propose, average, approach, discriminative, performance] [beta, computed, computation, larger] [divergence, error, matrix, covariance, robust, method, rate, true, objective, order, analysis, outlier, variance, orthogonal, basis, subspace, symmetric, optimization, largest, projection, denotes, number] [data, figure, probability, distribution, three] [theorem, function, note, problem, proof, solution, maximization, estimator, framework, statistical, linear] [csp, spatial, eeg, motor, rotation, term, neural, artifactual, trial, ieee, mcde, imagery, property, supplement, subject, pattern, novel, signal, brain, artifact, angle, activity, korea]
Robust Sparse Principal Component Regression under the High Dimensional Elliptical Model
Fang Han, Han Liu
Fang Han, Han Liu
[heavy, optimal, stock, bounded, advantage, return, day] [vector, prediction, tail, performance, scale, compared] [liu, larger, structure] [principal, elliptical, sparse, square, matrix, high, robust, random, covariance, leading, proposed, dimensional, rate, tau, rank, indexed, analysis, han, conducting, method, error, low, rpcr, featuresaveraged, convergence, pca, arxiv, semiparametric, eigenvectors, preprint, eigenvector] [component, data, model, gaussian, multivariate, distribution, figure, estimate, log, family, sample, equation, independent, journal, selected, estimation, power, plot, illustrate, three, truncated, parametric, statistic] [regression, classical, linear, estimator, consider, estimating, statistical, empirical, proposition, denote, set, dimension, theorem, condition, version, paper, quantile, lasso, interested] []
Lasso Screening Rules via Dual Polytope Projection
Jie Wang, Jiayu Zhou, Peter Wonka, Jieping Ye
Jie Wang, Jiayu Zhou, Peter Wonka, Jieping Ye
[optimal, sequence, identify, fact, safe, sequential] [vector, based, feature, performance, randomly, average, report, demonstrate, coil, learning, mnist, compare] [group, synthetic, construct, real, develop, developed, hand, path, size, compute] [dual, projection, matrix, sparse, convex, regularization, solving, proposed, standard, number, optimization, solve, sphere] [data, dpp, journal, time, parameter, three, exact, series, figure] [lasso, problem, screening, set, inactive, solution, theorem, effective, inequality, active, feasible, dome, corollary, enhanced, closed, kkt, gdpp, statistical, suppose, version, sgdpp, linear, royal, olivetti, geometric, polytope, easy, regression, society, general, solver] [response, rule, side, corresponding, refer, strong, ieee]
Similarity Component Analysis
Soravit Changpinyo, Kuan Liu, Fei Sha
Soravit Changpinyo, Kuan Liu, Fei Sha
[algorithm, assume, observe, apply, competing, attains] [similarity, sca, learning, metric, multiple, prediction, feature, well, lmnn, table, large, learn, better, randomly, dataset, learned, based, work, propose, class, representing, dissimilar, report, margin, task, illustrated] [local, link, network, synthetic, pair, probabilistic, nearest, social, edge, inference, disjoint, computed, compute] [distance, analysis, diagonal, number, sparse, row] [latent, data, model, component, modeling, positive, probability, likelihood, measure, journal, respect, conditional] [note, consider, machine, subset, set, select, multiway, problem] [man, corresponding]
Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs
Vikash Mansinghka, Tejas D. Kulkarni, Yura N. Perov, Josh Tenenbaum
Vikash Mansinghka, Tejas D. Kulkarni, Yura N. Perov, Josh Tenenbaum
[assume, uncertainty, conference, algorithm, programming] [image, generative, computer, vision, based, accuracy, approach, text, recognition, automatic, input, test, segmentation, training, report, character, original, detection, international, learning] [probabilistic, inference, global, local, existing, computation, developed, build, reading] [stochastic, random, high, letter, row, number, written] [model, approximate, figure, likelihood, bayesian, road, latent, data, posterior, processing, gaussian, observed, including, sampling] [program, problem, main, hard, tolerance, result] [scene, renderer, blur, control, appearance, gpgp, rendered, pattern, captcha, ieee, frame, single, interpretation, complex, stochasticity, system, degraded, generator, rendering, spatial, code, highly, typical, neural, captchas, simple]
Correlations strike back (again): the case of associative memory retrieval
Cristina Savin, Peter Dayan, Mate Lengyel
Cristina Savin, Peter Dayan, Mate Lengyel
[optimal, current, total, assume] [learning, weight, work, performance, well, wij] [network, binary, induced, local, cascade] [covariance, matrix, number] [distribution, additive, nonlinear, form, exact, observed, model, derived, computational, longer, transition, probability] [linear, function, case, strictly, consider, depend, problem, statistical] [synaptic, activity, neural, neuron, retrieval, rule, recall, pattern, simple, feedback, stored, plasticity, memory, term, neuroscience, correlated, account, gated, recurrent, storing, inhibition, hebbian, dendritic, postsynaptic, nature, palimpsest, reciprocal, experimentally, biological, decoding, ignoring, corresponding, partner, neuronal, decoder, storage, integration, induce, xor, sharing, homeostatic, modulation, coding]
Variational Inference for Mahalanobis Distance Metrics in Gaussian Process Regression
Michalis Titsias, Miguel Lazaro-Gredilla
Michalis Titsias, Miguel Lazaro-Gredilla
[bound, interesting, space] [training, input, learning, representation, large, approach, datasets, vector, applied, scale, type, work, performance, metric, relevance] [allows, inference, mahalanobis, variable, size] [method, number, matrix, dimensionality, distance, sparse, reduction, projection, variance, supplementary, divergence, standard, random] [variational, kernel, hyperparameters, gaussian, prior, full, bayesian, latent, model, vdmgp, standardised, distribution, process, data, inducing, nlpd, nmse, exponential, conditional, figure, referred, spgp, log, approximate, posterior, auxiliary, optimisable, considered, temp, puma] [function, regression, set, linear, density, machine, consider, squared, depend, framework, procedure, lower, case, dimension] [term, described, depends, novel, neural, property, typical]
Approximate Gaussian process inference for the drift function in stochastic differential equations
Andreas Ruttor, Philipp Batz, Manfred Opper
Andreas Ruttor, Philipp Batz, Manfred Opper
[state, algorithm, black, manfred, assume, difference, arbitrary] [well, vector, prediction, based, learning, large] [path, inference, diffusion, microscopic, regular, computed] [sparse, stochastic, order, variance, true, matrix, denotes, standard, number] [drift, posterior, process, time, gaussian, model, data, approximate, estimate, likelihood, marginal, transition, processing, kernel, estimation, sde, expectation, bayesian, replaced, exact, nonparametric, variational, double, rbf, grid, measure, multivariate, component, prior, figure, sample, observation, sampling, discrete, markov] [function, approximation, differential, set, density, polynomial, case, approximated, linear, point, interval] [dynamical, corresponding, neural, estimated, term, red, stable, simple, simulated, functional]
A Graphical Transformation for Belief Propagation: Maximum Weight Matchings and Odd-Sized Cycles
Jinwoo Shin, Andrew E. Gelfand, Misha Chertkov
Jinwoo Shin, Andrew E. Gelfand, Misha Chertkov
[algorithm, belief, step, programming, introduce, add, current, converged] [weight, transformation, performance, class, report, work, approach] [ynew, factor, assignment, variable, graph, edge, associated, graphical, cycle, propagation, path, matchings, child, correctness, parent, heuristic, inference, decrease, tree, structure, motivates, disjoint, tightness] [convergence, matching, solving, number, random, small, method] [time, probability] [mwm, lemma, map, problem, solution, proof, case, set, maximum, theorem, relaxation, max, condition, consider, exists, tight, linear, converges, construction, solver, design, odd, theoretical, provide, result, integral, establish, blossom, note] [correct, corresponding, leave]
Online Learning of Dynamic Parameters in Social Networks
Shahin Shahrampour, Sasha Rakhlin, Ali Jadbabaie
Shahin Shahrampour, Sasha Rakhlin, Ali Jadbabaie
[state, regret, msd, lim, bound, agent, optimal, online, upper, innovation, assume, aim, assumption, lkn, sequential, complete, satisfy, noting, making] [learning, prediction, weight, average, based, learn, vector, work] [network, social, underlying, steady, distributed, edge, communication, global, update, sensor, local, structure, graph] [rate, pij, random, true, optimization, error, analysis, matrix, proposed, decomposition, averaging, noisy, quadratic, mild] [time, parameter, observation, estimate, positive, journal, process] [loss, function, problem, consider, proposition, theorem, private, lower, ratio, technical, min, case, denote, tight, corollary, linear, studied, establish, unbiased] [signal, change, study, ieee, connection, kalman, noise, dynamic]
Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space
Xinhua Zhang, Wee Sun Lee, Yee Whye Teh
Xinhua Zhang, Wee Sun Lee, Yee Whye Teh
[bounded, space, optimal, appendix] [learning, vector, labeled, invariant, training, transformation, unlabeled, based, compared, test, svm, feature, input, target, class, approach] [local, product, allows, graph, induced, scaling, mit, laplacian] [number, optimization, gradient, norm, error, convex, coordinate, operator, order, analysis, method, standard, objective, basis] [data, kernel, gaussian, respect, inner, university, reproducing, hilbert, figure, sample, derivative, probability, model] [linear, function, invariance, loss, functionals, invsvm, theorem, rkhs, framework, representer, support, machine, result, lapsvm, representers, example, density, set, polynomial, consider, cost, squared, suppose, virtual, risk, commonly, proof, batch, lower, invsvmerror] [functional, change]
Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions
Yasin Abbasi, Peter Bartlett, Varun Kanade, Yevgeny Seldin, Csaba Szepesvari
Yasin Abbasi, Peter Bartlett, Varun Kanade, Yevgeny Seldin, Csaba Szepesvari
[algorithm, online, regret, policy, state, action, mdp, adversarial, parity, chosen, adversary, decision, round, choose, learner, adversarially, start, chooses, space, csaba, special, computationally, sequence, linearly, goal, assumption, changing, episodic, bound, bounded, suffers, deterministic, choice, designing, neu] [learning, class, weight, large, layer] [path, shortest, graph, edge, node] [stochastic, number, small, random, noisy, comparison] [transition, respect, log, markov, probability, time, figure, kernel, distribution, mixing, full] [loss, problem, set, function, case, result, theorem, consider, note, agnostic, linear, hard, denote, design, hardness, exists, constant] [change, study]
Distributed Submodular Maximization: Identifying Representative Elements in Massive Data
Baharan Mirzasoleiman, Amin Karbasi, Rik Sarkar, Andreas Krause
Baharan Mirzasoleiman, Amin Karbasi, Rik Sarkar, Andreas Krause
[greedy, algorithm, round, maximizing, best, chosen, optimal, assume] [large, approach, performance, learning, randomly, scale, performed, based, well, exemplar, second, dataset, vector, work, good, competitive, entire, evaluation] [distributed, parallel, size, clustering, ground, local, merged, reduce, partition, cluster, representative, associated] [standard, number, method, running, objective, uniformly, requires, performs, require] [data, element, probability, gaussian, time] [set, submodular, greedi, solution, function, machine, centralized, problem, maximization, monotone, active, theorem, cardinality, mapreduce, selection, result, subset, close, tiny, massive, general, approximation, andreas, provide, lazy, maximum, consider, decomposable, style, optimum, protocol, point] [varying]
Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion
Nguyen Viet Cuong, Wee Sun Lee, Nan Ye, Kian Ming A. Chai, Hai Leong Chieu
Nguyen Viet Cuong, Wee Sun Lee, Nan Ye, Kian Ming A. Chai, Hai Leong Chieu
[policy, adaptive, algorithm, greedy, setting, learner, maximizing, sequence, expected, selects, space, best, selecting, deterministic, observing, optimal, conference, called, sampled, uncertainty, choosing] [learning, unlabeled, labeled, text, task, training, performance, international] [probabilistic, tree, size, compute, summation, binary] [error, random, objective, small, number, reduction, noisy] [gibbs, entropy, bayesian, posterior, model, selected, conditional, prior, naive, distribution, bayes, shannon, probability, equation, crf, drawn, remaining, approximate, estimate, sample, sampling] [batch, active, maxgec, set, label, maximum, criterion, example, labeling, theorem, version, transductive, hypothesis, select, approximation, arg, case, submodular, map, passive, pool, query, proof, max, structured, budget, equivalent] []
Global Solver and Its Efficient Approximation for Variational Bayesian Low-rank Subspace Clustering
Shinichi Nakajima, Akiko Takeda, S. Derin Babacan, Masashi Sugiyama, Ichiro Takeuchi
Shinichi Nakajima, Akiko Takeda, S. Derin Babacan, Masashi Sugiyama, Ichiro Takeuchi
[free, algorithm, exp, computationally, assume] [large, propose, dataset, learning, segmentation, applied] [global, clustering, computation, probabilistic, local, search, inference] [subspace, mvga, iteration, agvbs, matrix, homotopy, unknown, rank, method, egvbs, lrsc, svb, written, small, optimization, proposed, standard, hopkins, japan, pca, denotes, diagonal, factorization, variance, dimensional, robust, sparse, freedom, additional, requires, solves, spectral, tokyo] [bayesian, stationary, variational, exact, figure, approximate, parameter, equation, gaussian, posterior, observed, model, time, data, log, computational, hyperparameters, bayes, selected] [solution, polynomial, energy, solver, approximation, problem, point, condition, set, theorem, machine, complexity, map] [system, estimated, noise, single]
Thompson Sampling for 1-Dimensional Exponential Family Bandits
Nathaniel Korda, Emilie Kaufmann, Remi Munos
Nathaniel Korda, Emilie Kaufmann, Remi Munos
[jeffreys, thompson, bound, arm, step, optimal, bandit, regret, algorithm, upper, choosing, introduce, conference, reward, previous, called, bounded, appendix, choice, round, numerator, chosen, special, generalising, exp, quantity, state, expected] [learning, fisher, work, second, bounding, knowledge, invariant] [concentration, belong, event] [canonical, divergence, number, unknown, analysis] [prior, exponential, sampling, posterior, distribution, family, probability, sample, parameter, bernoulli, time, parametric, observation, bayesian, asymptotic, measure] [proof, lemma, theorem, result, lower, note, inequality, exists, constant, empirical, proposition, provide, problem, asymptotically, function, general, risk, linear, theoretical, machine, main, theory] [term, uniform, interest]
Learning with Noisy Labels
Nagarajan Natarajan, Inderjit Dhillon, Pradeep Ravikumar, Ambuj Tewari
Nagarajan Natarajan, Inderjit Dhillon, Pradeep Ravikumar, Ambuj Tewari
[algorithm, setting, online, benchmark, best, optimal, fact, decision, appendix] [learning, accuracy, class, dataset, performance, training, corrupted, approach, competitive, based, work] [weighted, synthetic, symmetry] [noisy, convex, random, method, proposed, robust, true, stochastic, small, analysis] [data, distribution, bayes, probability, sample, kernel, respect, positive, iid, figure, observed] [loss, risk, function, label, unbiased, problem, minimization, empirical, lemma, clean, theorem, consider, result, proxy, surrogate, set, provide, main, min, hinge, stempfel, nherd, general, biconjugate, note, case, suitably, complexity, minimizing] [noise, minimizer, presence, simple, uniform, study, perceptron, threshold]
Online Learning with Switching Costs and Other Adaptive Adversaries
Nicolò Cesa-Bianchi, Ofer Dekel, Ohad Shamir
Nicolò Cesa-Bianchi, Ofer Dekel, Ohad Shamir
[adversary, regret, bounded, bandit, switching, player, oblivious, action, sequence, round, adaptive, bound, expected, upper, setting, algorithm, online, assume, chooses, game, fll, stock, observes, strategy, previous, chosen, special, logarithmic, arbitrary, called, follow, current, choose, investor, assumption, hedge, best, expert, conference, observe] [learning, table, prediction, work, performance, entire, international, better, based, competitive] [size, randomized] [random, number, standard, supplementary, reduction, stochastic, additional, analysis] [log, drift, respect, full, time] [loss, lower, function, proof, prove, interval, general, theorem, note, problem, denote, case, consider, guarantee, set, result] [memory, feedback, range, depends, described, simple]
Deep Fisher Networks for Large-Scale Image Classification
Karen Simonyan, Andrea Vedaldi, Andrew Zisserman
Karen Simonyan, Andrea Vedaldi, Andrew Zisserman
[projected] [fisher, image, layer, feature, learning, deep, pooling, vector, performance, stacking, large, training, dense, sift, discriminative, convolutional, trained, visual, class, recognition, conventional, shallow, input, svm, window, object, cnn, pipeline, representation, architecture, approach, table, evaluation, computer, densely, improve, carried, test, discriminatively, imagenet, accuracy, based, employed, extraction, stacked, pyramid, baseline, scale, applied] [network, computed, fvs, local, global, computation, corresponds] [dimensionality, projection, number, reduction, standard, pca, require, sparse, small, compressed, explained] [model] [set, linear, gmm, case, subset, note] [spatial, encoding, single, neural, encoder, coding, spatially]
Designed Measurements for Vector Count Data
Liming Wang, David Carlson, Miguel Rodrigues, David Wilcox, Robert Calderbank, Lawrence Carin
Liming Wang, David Carlson, Miguel Rodrigues, David Wilcox, Robert Calderbank, Lawrence Carin
[goal, provided, mirror, laser, assume] [vector, designed, class, based, input, output, word, performed, newsgroups, training] [chemical, represents, binary, versus, associated] [measurement, compressive, random, gradient, matrix, number, divergence, projection, denotes, error, rate, bregman, recovery] [poisson, mutual, gaussian, respect, model, figure, topic, data, document, dark, predictive, probability, observed, considered, mixture, estimation, dmd, binomial, estimate, conditional, count, full, processing, optical, optimized, latent, regularity, log, distribution, measure, entropy] [design, consider, set, case, theorem, note, mmse, paper, label, function] [scalar, channel, ieee, sensing, signal, relative, light, photon, system]
Memoized Online Variational Inference for Dirichlet Process Mixture Models
Michael Hughes, Erik Sudderth
Michael Hughes, Erik Sudderth
[online, algorithm, best, add, current, natural, previous, applicable] [learning, image, approach, large, compare, dataset, consistently, learned] [memoized, inference, local, global, elbo, merge, birth, merges, update, soa, truncation, merged, subsample, cluster, assignment, initialization, clustering, compute, escape, poor, allows, sob] [stochastic, pass, random, objective, method, true, exactly, covariance, rate, gradient, number, analysis, small] [data, variational, mixture, full, component, process, dirichlet, model, nonparametric, log, exponential, bayesian, figure, visiting, targeted, computational, entropy, discrete] [batch, set, effective, summary] []
Robust Transfer Principal Component Analysis with Rank Constraints
Yuhong Guo
Yuhong Guo
[transfer, algorithm, projected, best] [corrupted, target, large, image, denoising, learning, shared, based, performance, average, representation, reconstruction, applies, level, randomly] [source, structure, developed] [matrix, pca, robust, rank, method, optimization, convex, principal, recover, proposed, gradient, analysis, norm, nuclear, standard, dimensional, low, uncorrupted, singular, subspace, noisy, convenient, reduction, error, solve, dimensionality, small, recovering, conducted, number, basis, descent, high, solving, denotes, iterative, objective] [data, component, auxiliary, joint, observed, observation, figure, latent, parameter, rmse, gaussian] [problem, function, proximal, approximation, min, set, denote, minimization, framework, point, solution] [noise, effectively, intrinsic]
Universal models for binary spike patterns using centered Dirichlet processes
Il M. Park, Evan W. Archer, Kenneth Latimer, Jonathan Pillow
Il M. Park, Evan W. Archer, Kenneth Latimer, Jonathan Pillow
[computationally, choice, total] [word, large, good, performance, hierarchical, top] [binary, structure, inference, represents, supported] [number, sparse, order, convergence, divergence, small, written, proposed] [model, base, cascaded, measure, parametric, distribution, ising, data, ubm, nonparametric, probability, histogram, bernoulli, dirichlet, process, independent, entropy, likelihood, centered, maxent, figure, computational, log, bayesian, family, sample, predictive, observed, tractable, discrete, prior, naive, interaction, scatter, parameter, ubms, gaussian, estimate, retinal, drawn, modeling, three] [logistic, universal, provide, consider, note, converges, theorem, statistical, subset, ratio, empirical] [neural, spike, population, spiking, corresponding]
Learning Prices for Repeated Auctions with Strategic Buyers
Kareem Amin, Afshin Rostamizadeh, Umar Syed
Kareem Amin, Afshin Rostamizadeh, Umar Syed
[buyer, seller, price, algorithm, regret, revenue, strategic, surplus, setting, online, explore, repeated, round, discount, exploit, strategy, incentive, sequence, assume, truthful, previous, bound, future, selects, bandit, expected, reserve, auction, total, optimal, best, phased, notice, offered, compatible, advertising, choice, accepts, horizon, repeatedly, fact, appendix, electronic, goal, choose, rational, accepting, inventory, bid, maximizing, game] [learning, learn, maximize, work, better, good, multiple, well] [accept, web] [phase] [distribution, allocation, parameter, time, observed, drawn, respect] [lower, consider, lemma, set, note, problem, proof, interested, function, design, main, monotone, mechanism, exists] [behavior, receives, single, user]
Geometric optimisation on positive definite matrices for elliptically contoured distributions
Suvrit Sra, Reshad Hosseini
Suvrit Sra, Reshad Hosseini
[space, algorithm, state, previous] [class, metric, rich, negative] [structure, global, great, local, unique] [matrix, convex, key, iteration, running, covariance, convergence, elliptical, symmetric, solve, application, number, additional] [log, positive, multivariate, geodesic, nonlinear, manifold, time, parameter, data, geometry, riemannian, power, likelihood, estimation, form] [geometric, optimisation, hpd, convexity, function, corollary, general, theorem, result, theory, strictly, nonconvex, ecds, example, paper, statistical, weakly, set, point, elliptically, problem, contoured, inequality, map, solution, wider, kotz, condition, recognise, linear, version, dgfs, proof, lemma, max, main, recognising, converges, note, nonpositive, geodesically, cone, density, consider] [help, imaging, ieee, interest]
Optimal integration of visual speed across different spatiotemporal frequency channels
Matjaz Jogan, Alan Stocker
Matjaz Jogan, Alan Stocker
[optimal, assume, cumulative, provided, step, difference] [visual, test, based, well, multiple, predict, target, extracted, vision] [supported, processed, evidence, decrease] [phase, matching, reference, proposed, slower] [model, bayesian, likelihood, prior, data, independent, probability, distribution, figure, journal, assumed, posterior, full, var] [function, energy, hypothesis, consider] [speed, stimulus, perceived, frequency, channel, contrast, spatiotemporal, motion, discrimination, combined, response, individual, normalization, spatial, observer, relative, single, perception, integration, psychometric, normalized, sensory, complex, grating, drifting, coherent, account, slow, combination, neural, simple, psychophysical, percept, formulate, human, divisive, deg, physiological, stocker]
(More) Efficient Reinforcement Learning via Posterior Sampling
Ian Osband, Dan Russo, Benjamin Van Roy
Ian Osband, Dan Russo, Benjamin Van Roy
[regret, psrl, reinforcement, policy, mdp, algorithm, state, agent, optimal, optimistic, sampled, action, optimism, expected, reward, bellman, computationally, environment, riverswim, bound, start, selects, episode, episodic, thompson, conference, exploration, deterministic, regal, total, history, introduce, decision, strens, apply, programming, adaptive] [learning, performance, based, learn, outperforms, art, international, complicated, work] [allows, optimize, stanford, existing] [random, analysis, true, kth, high, error, order, unknown] [posterior, sampling, prior, time, distribution, probability, sample, bayesian, figure, expectation, markov, university, observed, length] [lemma, result, machine, theoretical, problem, provide, polynomial, function, consider, case] [strong, simple, dynamic, study]
Model Selection for High-Dimensional Regression under the Generalized Irrepresentability Condition
Adel Javanmard, Andrea Montanari
Adel Javanmard, Andrea Montanari
[assume, deterministic, assumption, bound, bounded, introduce, adaptive, computationally] [vector, large, work] [size, larger, variable] [random, matrix, covariance, high, standard, recovers, analysis, minimum, sign, order, required, orthogonal, method, eigenvalue] [model, gaussian, log, parameter, restricted, sample, probability, journal, covariates] [lasso, irrepresentability, support, condition, selection, design, generalized, estimator, consider, selector, lemma, theorem, problem, prove, correctly, signed, case, regression, set, empirical, min, general, note, stated, paper, superset, result, dantzig, gic, denote, linear, active, example, weaker, annals, exists, arg, constant, consistency, letting] [simple, correct, estimated, response, ieee, signal, refer]
Reciprocally Coupled Local Estimators Implement Bayesian Information Integration Distributively
Wenhao Zhang, Si Wu
Wenhao Zhang, Si Wu
[height, optimal, exp, optimally, dominating, setting] [input, visual, weak, achieve, multiple, smoothly, accuracy] [network, implement, inference, local, coupled, represents, strength, connected, decrease] [direction, variance, order, alm, denotes, wide] [bayesian, independent, gaussian, journal, model, three, positive, stationary, figure, estimate, continuous, limit, interaction] [consider, result, mechanism, condition, theoretical] [reciprocal, bump, position, decoding, heading, vestibular, neuroscience, external, cue, integration, neural, experimental, stimulus, mstd, brain, motion, nature, connection, vip, reciprocally, sensory, ext, integrate, receives, reliable, single, excitatory, mimicking, property, noise, jrp, synaptic, preferred, inhibitory, recurrent, shape, range, calculate, stable, study, attractor, supplemental, determined]
Top-Down Regularization of Deep Belief Networks
Hanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim
Hanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim
[belief, previous, algorithm, strategy, sampled, current] [learning, deep, rbm, layer, supervised, training, unsupervised, rbms, input, recognition, vector, image, building, dataset, discriminative, representation, object, dbn, based, output, boltzmann, generative, class, forward, backward, stacked, mnist, table, second, trained, digit, handwritten, backpropagation, regularize, setup, initialized, learned, convolutional, visual, performed, feature] [network, existing, update] [phase, error, method, regularized, regularization, divergence, sparse, alternating, pass, gradient, optimization, rate, number, descent, block, random] [latent, sampling, model, figure, contrastive, restricted, distribution, parameter, data, gibbs, log, likelihood, form] [set, function, map] [neural, spatial]
Scalable Influence Estimation in Continuous-Time Diffusion Networks
Nan Du, Le Song, Manuel Gomez-Rodriguez, Hongyuan Zha
Nan Du, Le Song, Manuel Gomez-Rodriguez, Hongyuan Zha
[algorithm, appendix, greedy, expected, maximizing, previous, current] [window, accuracy, work, approach, based, scale, compare, large] [node, transmission, source, diffusion, network, infected, size, cascade, continest, neighborhood, directed, randomized, edge, increasing, scalable, graphical, list, social, real, jure, infection, shortest, smallest, manuel, reachable, synthetic, graph, path, generate, heterogeneous, hongyuan] [random, number, error, distance, additional, true] [time, estimation, independent, model, sampling, estimate, selected, log, exponential, data, computational, draw, sample, naive, modeling, figure, probability, continuous, process] [set, problem, maximization, label, density, complexity, function, estimating, design] [estimated, single]
Fast Determinantal Point Process Sampling with Application to Clustering
Byungkon Kang
Byungkon Kang
[algorithm, initial, current, previous, choose, state, return, introduce] [similarity, large, better, table, approach] [clustering, size, search, induced, partition, computed, cluster, perform, compute, update, represent, computation, inference] [matrix, number, distortion, computing, requires, running, proposed, small, spectral, order, require, analysis, fast, updated] [chain, sampling, sample, time, markov, dpp, distribution, probability, mixing, data, kernel, determinant, kkm, inverse, element, transition, stationary, pwc, dpps, computational, positive, figure, dbscan, full, process] [set, point, complexity, problem, procedure, ratio, result, subset, note, consider, map, cost] [determinantal, corresponding, single, rapidly]
Information-theoretic lower bounds for distributed statistical estimation with communication constraints
Yuchen Zhang, John Duchi, Michael Jordan, Martin J. Wainwright
Yuchen Zhang, John Duchi, Michael Jordan, Martin J. Wainwright
[minimax, bound, total, optimal, logarithmic, bounded, assume, decentralized] [based, achieve, vector, class, amount, learning] [distributed, communication, message, size, local, send, center, supported, allows] [number, rate, error, required, unknown, random, order, solving, denotes] [log, estimation, sample, family, independent, data, distribution, parameter, model, normal, estimate, dependence, length] [lower, machine, regression, statistical, problem, constant, centralized, budget, consider, interactive, linear, fusion, probit, protocol, universal, lemma, proposition, corollary, design, suppose, function, risk, proof, theorem, main, inequality, subset, general, max, turn, min, set, result, denote, classical, sends, minimal] [uniform, sharp, receives, single, study, achievable, location, ieee]
Projected Natural Actor-Critic
Philip S. Thomas, William C. Dabney, Stephen Giguere, Sridhar Mahadevan
Philip S. Thomas, William C. Dabney, Stephen Giguere, Sridhar Mahadevan
[natural, policy, projected, mirror, space, optimal, safe, algorithm, state, step, safety, arm, pnac, unconstrained, reinforcement, compatible, png, muscle, notice, controller, converge, resides, nac, electrical, action, conference, reward, psg, return] [learning, class, applied, metric, negative, training] [search, update, den, move, size] [gradient, descent, projection, constrained, euclidean, convex, matrix, objective, direction, standard, call, project] [figure, form, estimate, university, model, volume, locally, include, markov, log] [function, set, case, proximal, point, solution, equivalent, problem, consider, subgradient, example, unbiased, result] [region, control, human, stable, dynamic, ieee, simulated, functional, robot, principled, stimulation, angle]
Convex Two-Layer Modeling
Özlem Aslan, Hao Cheng, Xinhua Zhang, Dale Schuurmans
Özlem Aslan, Hao Cheng, Xinhua Zhang, Dale Schuurmans
[algorithm, optimal, assumption, assume] [training, layer, learning, second, approach, test, deep, feature, representation, jointly, input, output, vector, boosting, large, trained, work, based, architecture, applied, margin, demonstrate, prediction, negative] [variable, structure, clustering, local, inference, allows] [convex, objective, method, adopt, sparse, optimization, matrix, key, proposed] [latent, data, model, conditional, kernel, modeling, figure, remains, form, nonlinear, observed, three, component] [min, loss, problem, consider, relaxation, set, lemma, note, result, transductive, machine, main, label, simply, denote, establish, solution, equivalence] [single, response, capture, neural, highly]
Understanding Dropout
Pierre Baldi, Peter J. Sadowski
Pierre Baldi, Peter J. Sadowski
[difference, assume, satisfy, previous] [dropout, unit, input, whl, training, learning, layer, applied, subnetworks, hidden, large, second, trained, feature, average, output, fan, better, good, deep, oen] [ensemble, weighted, network, propagation] [gradient, error, small, variance, true, stochastic, order, random, averaging, sparse, regularization, performs, regularized, descent] [equation, figure, expectation, three, bernoulli, independent, university, distribution, probability, respect, een] [approximation, geometric, linear, consistency, inequality, case, logistic, set, constant, consider, active, example, result, function] [neuron, neural, activity, single, normalized, sigmoidal, described, typical, gating, term, simple, higher]
Estimation, Optimization, and Parallelism when Data is Sparse
John Duchi, Michael Jordan, Brendan McMahan
John Duchi, Michael Jordan, Brendan McMahan
[algorithm, assumption, minimax, optimal, natural, adaptive, bound, assume, online, best, impact, computes, conference] [training, learning, vector, achieve, dataset, test, type, performance, accuracy] [asynchronous, parallel, collection, update, versus, develop] [number, optimization, asyncda, stepsize, stochastic, gradient, dual, adagrad, asyncadagrad, sparsity, rate, sparse, convex, convergence, speedup, error, random, coordinate, denotes, standard, pjm, averaging, analysis, performs, require] [data, figure, sample, log, time, parameter] [set, theorem, proposition, corollary, machine, statistical, condition, lower, loss, consider, provide, linear, note, function, constant, inf, url] [relative, study, addition]
A multi-agent control framework for co-adaptation in brain-computer interfaces
Josh S. Merel, Roy Fox, Tony Jebara, Liam Paninski
Josh S. Merel, Roy Fox, Tony Jebara, Liam Paninski
[optimal, agent, assume, current, setting, state, horizon, initial, algorithm] [target, improve, performance, approach, performed, learning, task, well, med, work] [update, factor, corresponds, real, hand, optimize] [error, standard, quadratic, updated] [model, estimate, process, estimation, figure, stationary, parameter, simulation, observed, journal, time] [cost, procedure, linear, point, case, function, problem, consider, solution, framework] [decoder, neural, encoder, control, user, encoding, bci, decoding, signal, feedback, intention, noise, response, kalman, decoded, forgetting, timestep, system, adaptation, presented, motor, electrode, interface, ieee, experimental, tuning, lqr, simulated, position, conf, eng, intended, correspond, side]
Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC
Roger Frigola, Fredrik Lindsten, Thomas B. Schon, Carl Rasmussen
Roger Frigola, Fredrik Lindsten, Thomas B. Schon, Carl Rasmussen
[state, algorithm, step] [learning, approach, learned, learn, truth, based, applied] [inference, ground, variable] [sparse, matrix, covariance, standard, implementation, measurement, number] [model, particle, distribution, sampling, smoothing, prior, time, transition, gaussian, latent, ancestor, parametric, computational, monte, carlo, process, markov, predictive, sample, figure, inducing, form, chain, nonlinear, joint, processing, data, nonparametric, fic, gaussians, likelihood, observation, bayesian, mixture, posterior, full, address, rmse, pgas, referred, expression, vanilla, kernel, conditionally, tailored] [function, set, approximation, complexity, problem, note, consider, regression, density, cost, case] [system, dynamical, trajectory, fully, neural, marginalizing, corresponding]
Sketching Structured Matrices for Faster Nonlinear Regression
Haim Avron, Vikas Sindhwani, David Woodruff
Haim Avron, Vikas Sindhwani, David Woodruff
[algorithm, space, choice, best, deterministic] [vector, embedding, class, embeddings, approach, accuracy] [compute, randomized, structure, product, computed, size, symposium, degree, annual, sketch] [matrix, random, number, fourier, fast, subspace, sketching, faster, sparse, norm, vandermonde, error, multiplication, diagonal, column, small, basis, solves, solving, speedup, stoc, woodruff, running, robust, analysis, sparsity, supplementary] [time, probability, additive, gaussian, kernel, log, nonlinear, figure, parameter, sampling, distribution, multivariate, sample, modeling, exponential] [regression, structured, polynomial, theorem, set, linear, lemma, problem, consider, approximation, design, function, solution, provide, case, theory, proof, machine, statistical, constant, suppose] [constraint, simultaneously]
Speeding up Permutation Testing in Neuroimaging
Chris Hinrichs, Vamsi Ithapu, Qinyuan Sun, Sterling C. Johnson, Vikas Singh
Chris Hinrichs, Vamsi Ithapu, Qinyuan Sun, Sterling C. Johnson, Vikas Singh
[long, online] [datasets, test, multiple, dataset, training, entire, tail, large, level, based, work, randomly, extremely] [factor, global, corresponds, treatment, construct, disease] [permutation, matrix, number, low, speedup, rate, error, random, true, fwer, neuroimaging, recover, rank, completion, method, recovery, small, subsampling, high, singular, recovered, analysis, order, basis, require, spectrum, orthogonal] [null, sampling, testing, distribution, sample, estimate, residual, model, computational, data, statistic, time, bonferroni, plot, three, correction, figure, gaussian, tion, sst] [maximum, note, set, estimating, result, theorem, statistical, approximation] [estimated, threshold, strong, study, imaging, highly, change, trial, brain, artifact]
Regret based Robust Solutions for Uncertain Markov Decision Processes
Asrar Ahmed, Pradeep Varakantham, Yossiri Adulyasak, Patrick Jaillet
Asrar Ahmed, Pradeep Varakantham, Yossiri Adulyasak, Patrick Jaillet
[regret, uncertainty, policy, optimal, decision, uncertain, cer, reward, action, cregt, state, step, creg, expected, cumulative, maximin, mdps, provided, algorithm, minimax, conference, greedy, exploit, integer, horizon, milp, worst, difference, deterministic, variant, break, dominated, denoted] [learning, performance] [product, computation, represent, existing, randomized, size, scalable] [number, robust, error, denotes, analysis, comparison, random, key] [sample, time, markov, transition, sampling, equation, distribution, independent, independence, figure, probability] [set, provide, max, proposition, case, minimizing, min, approximation, proof, maximum, linear, denote, solution, function, problem, arg] [corresponding, supplement, dependent, dynamic, range, indicate, simulated]
Direct 0-1 Loss Minimization and Margin Maximization with Boosting
Shaodan Zhai, Tian Xia, Ming Tan, Shaojun Wang
Shaodan Zhai, Tian Xia, Ming Tan, Shaojun Wang
[algorithm, greedy, optimal, maximizing, decision] [margin, training, weak, average, bottom, boosting, lpboost, avg, directboost, adaboost, learning, directboostorder, directly, well, test, maximize, intercept, table, gaverage, validation, negative, brownboost, ith, datasets, better, increment, performance, logitboost, coordinatewise, direct] [compute, update, ensemble, increasing, depth] [error, coordinate, ascent, minimum, method, convex, descent, number, rate, column, random, soft, convergence, largest, sign] [data, sample, figure, positive, derivative, three] [set, example, loss, linear, function, maximizes, label, empirical, uci, theorem, interval, point, denote, consider, machine, minimizes, case, annals, theory, converges, problem, minimization, maximum, monotonically, adult, intersection, solution] [noise, side, region, slope, described]
Robust Data-Driven Dynamic Programming
Grani Adiwena Hanasusanto, Daniel Kuhn
Grani Adiwena Hanasusanto, Daniel Kuhn
[rddp, state, programming, ddp, exogenous, wind, decision, endogenous, algorithm, optimal, day, historical, uncertainty, assumption, action, policy, expected, nominal, best, commitment, reinforcement, assume] [tracking, vector, well, international, type, weight, approach, learning, evaluate] [represents] [robust, optimization, convex, quadratic, true, stochastic, high, persistence, typically] [conditional, distribution, sample, approximate, estimate, figure, data, expectation, kernel, estimation, markov, journal, time, probability, observation, piecewise, dependence, computational, generated] [function, energy, set, cost, problem, min, approximation, estimator, case, program, solution, linear, note, distributional, bias, regression, example, machine] [dynamic, control, storage, estimated, dominates]
Low-Rank Matrix and Tensor Completion via Adaptive Sampling
Akshay Krishnamurthy, Aarti Singh
Akshay Krishnamurthy, Aarti Singh
[algorithm, adaptive, space, bound, sequential, total, setting, worse, benjamin] [learning, vector, work, performance, large, detection] [candidate, existing, missing, symposium, factor] [matrix, completion, tensor, column, subspace, rank, row, incoherence, number, noisy, norm, success, order, nuclear, convex, low, exactly, recover, basis, arxiv, error, preprint, additional, nystrom, singular, emmanuel, recovering, random, require, balzano] [probability, sampling, sample, dependence, figure, log, data, exact, observed, journal, parameter, estimation] [theorem, complexity, passive, procedure, machine, set, result, problem, subset, lower, linear, theoretical, constant, function, corollary, approximation, adaptivity, theory, note, selection] [study, highly, uniform, ieee, noiseless]
Learning Multi-level Sparse Representations
Ferran Diego Andilla, Fred A. Hamprecht
Ferran Diego Andilla, Fred A. Hamprecht
[sequence, expected, conference, space, upper] [dictionary, learning, image, detection, raw, segmentation, activation, performance, unsupervised, well, hierarchical, concept, level, jointly] [synthetic, structure, allows, assignment, associated, relation, real, ground, adjacency] [matrix, sparse, number, factorization, decomposition, basis, proposed, analysis, sparsity, precision, impose, convex, optimization, application, method] [data, time, figure, estimate, component] [set, structured, case, approximation, active] [calcium, neuronal, bilevel, single, temporal, imaging, assembly, shmf, cell, activity, neuron, heterarchical, sensitivity, spatial, transient, supplemental, individual, described, adina, ieee, infer, signal, overlap, estimated, contrast, simultaneously]
Distributed Exploration in Multi-Armed Bandits
Eshcar Hillel, Zohar S. Karnin, Tomer Koren, Ronny Lempel, Oren Somekh
Eshcar Hillel, Zohar S. Karnin, Tomer Koren, Ronny Lempel, Oren Somekh
[arm, algorithm, player, best, mab, identify, exploration, round, bandit, strategy, reward, bound, explore, goal, optimal, choose, vote, communicate, arbitrary, assume, regret, setting, haifa, communicates, expected, focus] [learning, approach, work, multiple, identifying, yahoo, achieve, output, reasonable, performance, accuracy, average, common] [communication, distributed, parallel, serial, factor, message, elimination] [number, random, high, allowing, stochastic, phase, analysis, collaborative, required, tradeoff] [probability, model, independent, majority, time, sample, log] [theorem, lemma, set, case, problem, lower, consider, prove, machine, result, correctly, subset, idea, empirical, selection, function, implies] [single, load]
The Pareto Regret Frontier
Wouter M. Koolen
Wouter M. Koolen
[regret, optimal, strategy, pareto, expert, absolute, realisable, frontier, state, contact, horizon, learner, algorithm, online, characterise, witness, hedge, lim, bound, follow, outcome, best, cumulative, peter, round, subsequently, play, characterisation, manfred, game, desire, ensure, jacob] [learning, large, prediction, tail, compared, achieved, dot, vector] [vertex, binary, candidate, recursive, tree, relation] [random, small, rate, number, warmuth, convex] [prior, probability, figure, journal, limit, processing, exact, log, remaining, form, time] [loss, set, lemma, case, consider, theorem, problem, asymptotically, studied, machine, linear, argument, point, general, approximation] [achievable, combination, neural, study, slope, single, curve]
Probabilistic Low-Rank Matrix Completion with Adaptive Spectral Regularization Algorithms
Adrien Todeschini, François Caron, Marie Chavent
Adrien Todeschini, François Caron, Marie Chavent
[algorithm, adaptive, complete, assume, initialize, incomplete, chosen] [hierarchical, test, large, approach, learning, datasets, compare, reported, table, propose] [missing, compute, weighted] [rank, matrix, low, nuclear, norm, singular, regularization, completion, jester, nmae, error, hasi, optimization, soft, svd, movielens, minimize, proposed, iteration, objective, supplementary, convex, true, thresholding, xij, hann, sparse, iteratively, averaged, minimum, recovers, solving] [distribution, figure, exponential, parameter, estimate, bayesian, journal, prior, data, mixture, observed, log, marginal, gaussian] [set, penalty, case, maximum, consider, problem, solution, machine, map, subset, derive, thresholded, provide, hard, lower, function, constant] [simulated, snr, user, estimated]