Ermon Group

2023

• Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski.
  Generative Modeling Helps Weak Supervision (and Vice Versa).
  To appear in Proc. 11th International Conference on Learning Representations (ICLR 2023).
• Xuan Su, Jiaming Song, Chenlin Meng, Stefano Ermon.
  Dual Diffusion Implicit Bridges for Image-to-Image Translation.
  To appear in Proc. 11th International Conference on Learning Representations (ICLR 2023).
• Divyansh Garg, Joey Hejna, Matthieu Geist, Stefano Ermon.
  Extreme Q-Learning: MaxEnt RL without Entropy.
  To appear in Proc. 11th International Conference on Learning Representations (ICLR 2023).
• Kuno Kim, Stefano Ermon.
  Understanding and Adopting Rational Behavior by Bellman Score Estimation.
  To appear in Proc. 11th International Conference on Learning Representations (ICLR 2023).
• Michael Poli, Stefano Massaroli, Stefano Ermon, Bryan Wilder, Eric Horvitz.
  Ideal Abstractions for Decision-Focused Learning.
  To appear in Proc. 26th International Conference on Artificial Intelligence and Statistics, (AISTATS 2023).
• Charles Marx, Youngsuk Park, Hilaf Hasson, Yuyang Wang, Stefano Ermon, Luke Huan.
  But Are You Sure? An Uncertainty-Aware Perspective on Explainable AI.
  To appear in Proc. 26th International Conference on Artificial Intelligence and Statistics, (AISTATS 2023).
• Lantao Yu, Tianhe Yu, Jiaming Song, Willie Neiswanger, Stefano Ermon.
  Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching.
  To appear in Proc. 37th AAAI Conference on Artificial Intelligence (AAAI 2023).

2022

• Chenlin Meng, Kristy Choi, Jiaming Song, Stefano Ermon.
  Concrete Score Matching: Generalized Score Matching for Discrete Data.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Willie Neiswanger, Lantao Yu, Shengjia Zhao, Chenlin Meng, Stefano Ermon.
  Generalizing Bayesian Optimization with Decision-theoretic Entropies.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Andy Shih, Dorsa Sadigh, Stefano Ermon.
  Training and Inference on Any-Order Autoregressive Models the Right Way (Oral Presentation).
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Michael Poli, Winnie Xu, Stefano Massaroli, Chenlin Meng, Kuno Kim, Stefano Ermon.
  Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Michael Poli, Stefano Massaroli, Federico Berto, Jinkyoo Park, Tri Dao, Christopher Ré, Stefano Ermon.
  Transform Once: Efficient Operator Learning in Frequency Domain.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Yezhen Cong, Samar Khanna, Chenlin Meng, Patrick Liu, Erik Rozi, Yutong He, Marshall Burke, David Lobell, Stefano Ermon.
  SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Divyansh Garg, Skanda Vaidyanath, Kuno Kim, Jiaming Song, Stefano Ermon.
  LISA: Learning Interpretable Skill Abstractions from Language.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Yann Dubois, Stefano Ermon, Tatsunori Hashimoto, Percy Liang.
  Improving Self-Supervised Learning by Characterizing Idealized Representations.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Viraj Mehta, Ian Char, Joseph Abbate, Rory Conlin, Mark Boyer, Stefano Ermon, Jeff Schneider, Willie Neiswanger.
  Exploration via Planning for Information about the Optimal Trajectory.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, Jun-Yan Zhu.
  Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Bahjat Kawar, Michael Elad, Stefano Ermon, Jiaming Song.
  Denoising Diffusion Restoration Models.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Tri Dao, Daniel Fu, Stefano Ermon, Atri Rudra, Christopher Ré.
  FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.
  In Proc. 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).
• Charles Marx, Shengjia Zhao, Willie Neiswanger, Stefano Ermon.
  Modular Conformal Calibration.
  In Proc. 39th International Conference on Machine Learning (ICML 2022).
• Rui Shu, Stefano Ermon.
  Bit Prioritization in Variational Autoencoders via Progressive Coding.
  In roc. 39th International Conference on Machine Learning (ICML 2022).
• Jiaming Song, Lantao Yu, Willie Neiswanger, Stefano Ermon.
  A General Recipe for Likelihood-free Bayesian Optimization.
  In Proc. 39th International Conference on Machine Learning (ICML 2022).
• Chenlin Meng, Linqi Zhou, Kristy Choi, Tri Dao, Stefano Ermon.
  ButterflyFlow: Building Invertible Layers with Butterfly Matrices.
  In Proc. 39th International Conference on Machine Learning (ICML 2022).
• Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani.
  Imitation Learning by Estimating Expertise of Demonstrators.
  In Proc. 39th International Conference on Machine Learning (ICML 2022).
• Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon.
  SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations.
  In Proc. 10th International Conference on Learning Representations (ICLR 2022).
• Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault, Jiaming Song, Stefano Ermon.
  Comparing Distributions by Measuring Differences that Affect Decision Making.
  In Proc. 10th International Conference on Learning Representations (ICLR 2022).
  ICLR Outstanding Paper Award.
• Viraj Mehta, Biswajit Paria, Jeff Schneider, Stefano Ermon, Willie Neiswanger.
  An Experimental Design Perspective on Exploration in Reinforcement Learning.
  In Proc. 10th International Conference on Learning Representations (ICLR 2022).
• Minkai Xu, Lantao Yu, Yang Song, Chence Shi, Stefano Ermon, Jian Tang.
  GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation.
  In Proc. 10th International Conference on Learning Representations (ICLR 2022).
• Yang Song, Liyue Shen, Lei Xing, Stefano Ermon.
  Solving Inverse Problems in Medical Imaging with Score-Based Generative Models.
  In Proc. 10th International Conference on Learning Representations (ICLR 2022).
• Kristy Choi, Chenlin Meng, Yang Song, Stefano Ermon.
  Density Ratio Estimation via Infinitesimal Classification.
  In Proc. 25th International Conference on Artificial Intelligence and Statistics (ICLR 2022).
• Chenlin Meng, Enci Liu, Willie Neiswanger, Jiaming Song, Marshall Burke, David Lobell, Stefano Ermon.
  IS-Count: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling.
  In Proc. 36th AAAI Conference on Artificial Intelligence (AAAI 2022).

2021

• Christopher Yeh, Chenlin Meng, Sherrie Wang, Anne Driscoll, Erik Rozi, Patrick Liu, Jihyeon Lee, Marshall Burke, David Lobell, Stefano Ermon.
  SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021 Datasets & Benchmarks Track).
• Lantao Yu, Jiaming Song, Yang Song, Stefano Ermon.
  Pseudo-Spherical Contrastive Divergence.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Chris Cundy, Aditya Grover, Stefano Ermon.
  Scalable Variational Approaches for Bayesian Causal Discovery.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Roshni Sahoo, Shengjia Zhao, Alyssa Chen, Stefano Ermon.
  Reliable Decisions with Threshold Calibration.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Chenlin Meng, Yang Song, Wenzhe Li, Stefano Ermon.
  Estimating High Order Gradients of the Data Distribution by Denoising.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Mike Wu, Noah Goodman, Stefano Ermon.
  Improving Compositionality of Neural Networks by Decoding Representations to Inputs.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Stefano Ermon.
  IQ-Learn: Inverse soft-Q Learning for Imitation (Spotlight Presentation).
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Yusuke Tashiro, Jiaming Song, Yang Song, Stefano Ermon.
  CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Yutong He, Dingjie Wang, Nicholas Lai, William Zhang, Chenlin Meng, Marshall Burke, David Lobell, Stefano Ermon.
  Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Shengjia Zhao, Michael P. Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon.
  Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon.
  D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Yang Song, Conor Durkan, Iain Murray, Stefano Ermon.
  Maximum Likelihood Training of Score-Based Diffusion Models (Spotlight Presentation).
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Andy Shih, Dorsa Sadigh, Stefano Ermon.
  HyperSPNs: Compact and Expressive Probabilistic Circuits.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Robin Swezey, Aditya Grover, Bruno Charron, Stefano Ermon.
  PiRank: Scalable Learning To Rank via Differentiable Sorting.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Kuno Kim, Akshat Jindal, Yang Song, Jiaming Song, Yanan Sui, Stefano Ermon.
  Imitation with Neural Density Models.
  In Proc. 35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021).
• Kumar Ayush, Burak Uzkent, Chenlin Meng, Kumar Tanmay, Marshall Burke, David Lobell, Stefano Ermon.
  Geography-Aware Self-Supervised Learning.
  In Proc. 18th International Conference on Computer Vision, (ICCV 2021).
• Kristy Choi, Madeline Liao, Stefano Ermon.
  Featurized Density Ratio Estimation.
  In Proc. 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021).
• Willie Neiswanger, Ke Alexander Wang, Stefano Ermon.
  Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information.
  In Proc. 38th International Conference on Machine Learning (ICML 2021).
• Yang Song, Chenlin Meng, Renjie Liao, Stefano Ermon.
  Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving.
  In Proc. 38th International Conference on Machine Learning (ICML 2021).
• Kuno Kim, Shivam Garg, Kirankumar Shiragur, Stefano Ermon.
  Reward Identification in Inverse Reinforcement Learning.
  In Proc. 38th International Conference on Machine Learning (ICML 2021).
• Tung Nguyen, Rui Shu, Tuan Pham, Hung Bui, Stefano Ermon.
  Temporal Predictive Coding For Model-Based Planning In Latent Space.
  In Proc. 38th International Conference on Machine Learning (ICML 2021).
• Jihyeon Lee, Nina Brooks, Fahim Tajwar, Marshall Burke, Stefano Ermon, David Lobell, Debashish Biswas, Stephen Luby.
  Scalable Deep Learning to Identify Brick Kilns and Aid Regulatory Capacity.
  In Proceedings of the National Academy of Sciences (PNAS), 27 Apr 2021, 118 (17). DOI: 10.1073/pnas.2018863118.
• Marshall Burke, Anne Driscoll, David B. Lobell, Stefano Ermon.
  Using Satellite Imagery to Understand and Promote Sustainable Development.
  In Science, 19 Mar 2021, Vol. 371, No. 6535. DOI: 10.1126/science.abe8628.
• Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole.
  Score-Based Generative Modeling through Stochastic Differential Equations.
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
  ICLR Outstanding Paper Award.
• Chenlin Meng, Jiaming Song, Yang Song, Shengjia Zhao, Stefano Ermon.
  Improved Autoregressive Modeling with Distribution Smoothing (Oral Presentation).
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
• Jiaming Song, Chenlin Meng, Stefano Ermon.
  Denoising Diffusion Implicit Models.
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
• Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon.
  Anytime Sampling for Autoregressive Models via Ordered Autoencoding.
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
• Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon.
  Negative Data Augmentation.
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
• Andy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh.
  On the Critical Role of Conventions in Adaptive Human-AI Collaboration.
  In Proc. 9th International Conference on Learning Representations (ICLR 2021).
• Shengjia Zhao, Stefano Ermon
  Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration.
  In Proc. 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021).
• Jihyeon Lee, Dylan Grosz, Sicheng Zeng, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon.
  Predicting Livelihood Indicators from Crowdsourced Street Level Images.
  In Proc. 35th AAAI Conference on Artificial Intelligence (AAAI 2021).
• Kumar Ayush, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon.
  Efficient Poverty Mapping from High Resolution Remote Sensing Images.
  In Proc. 35th AAAI Conference on Artificial Intelligence (AAAI 2021).

2020

• Jiaming Song, Stefano Ermon.
  Multi-label Contrastive Predictive Coding (Oral Presentation).
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Jonathan Kuck, Shuvam Chakraborty, Hao Tang, Rachel Luo, Jiaming Song, Ashish Sabharwal, Stefano Ermon.
  Belief Propagation Neural Networks.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Yang Song, Stefano Ermon.
  Improved Techniques for Training Score-Based Generative Models.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Chenlin Meng, Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon.
  Autoregressive Score Matching.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Andy Shih, Stefano Ermon.
  Probabilistic Circuits for Variational Inference in Discrete Graphical Models.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Yusuke Tashiro, Yang Song, Stefano Ermon.
  Diversity can be Transferred: Output Diversification for White- and Black-box Attacks.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, Christopher Ré.
  HiPPO: Recurrent Memory with Optimal Polynomial Projections (Spotlight Presentation).
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Tianyu Pang, Kun Xu, Chongxuan Li, Yang Song, Stefano Ermon, Jun Zhu.
  Efficient Learning of Generative Models via Finite-Difference Score Matching.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma
  MOPO: Model-based Offline Policy Optimization.
  In Proc. 34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020).
• Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon.
  Training Deep Energy-Based Models with f-Divergence Minimization.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Shengjia Zhao, Tengyu Ma, Stefano Ermon.
  Individual Calibration with Randomized Forecasting.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Jiaming Song, Stefano Ermon.
  Bridging the Gap Between f-GANs and Wasserstein GANs.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon.
  Domain Adaptive Imitation Learning.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, Stefano Ermon.
  Fair Generative Modeling via Weak Supervision.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Rui Shu, Tung Nguyen, Yinlam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung Bui.
  Predictive Coding for Locally-Linear Control.
  In Proc. 37th International Conference on Machine Learning (ICML 2020).
• Christopher Yeh, Anthony Perez, Anne Driscoll, Zhongyi Tang, George Azzari, David Lobell, Stefano Ermon, Marshall Burke.
  Using Publicly Available Satellite Imagery and Deep Learning to Understand Economic Well-Being in Africa.
  In Nature Communications, 11, 2583, 2020.
• Chris Cundy, Stefano Ermon.
  Flexible Approximate Inference via Stratified Normalizing Flows.
  In Proc. 36th Conference on Uncertainty in Artificial Intelligence (UAI 2020).
• Kumar Ayush, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon.
  Generating Interpretable Poverty Maps using Object Detection in Satellite Images.
  In Proc. 29th International Joint Conference on Artificial Intelligence (IJCAI 2020).
• Peter M. Attia, Aditya Grover, Norman Jin, Kristen A. Severson, Todor M. Markov, Yang-Hung Liao, Michael H. Chen, Bryan Cheong, Nicholas Perkins, Zi Yang, Patrick K. Herring, Muratahan Aykol, Stephen J. Harris, Richard D. Braatz, Stefano Ermon, William C. Chueh.
  Closed-loop Optimization of Fast-Charging Protocols for Batteries with Machine Learning.
  In Nature, 578, 397-402, 2020. [News]
  
• Joseph Duris, Dylan Kennedy, Adi Hanuka, Jane Shtalenkova, Auralee Edelen, Panagiotis Baxevanis, Adam Egger, Tyler Cope, Mitchell McIntire, Stefano Ermon, Daniel Ratner.
  Bayesian Optimization of a Free-Electron Laser.
  In Physical Review Letters, 124, 124801, 2020.
• Burak Uzkent, Stefano Ermon.
  Learning When and Where to Zoom with Deep Reinforcement Learning.
  In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020).
• Chenlin Meng, Yang Song, Jiaming Song, Stefano Ermon.
  Gaussianization Flows.
  In Proc. 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
• Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon.
  Permutation Invariant Graph Generation via Score-Based Generative Modeling. [Code]
  In Proc. 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
• Shengjia Zhao, Christopher Yeh, Stefano Ermon.
  A Framework for Sample Efficient Interval Estimation with Control Variates.
  In Proc. 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
• Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon.
  A Theory of Usable Information under Computational Constraints.
  In Proc. 8th International Conference on Learning Representations (ICLR 2020).
• Jiaming Song, Stefano Ermon.
  Understanding the Limitations of Variational Mutual Information Estimators.
  In Proc. 8th International Conference on Learning Representations (ICLR 2020).
• Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole.
  Weakly Supervised Disentanglement with Guarantees.
  In Proc. 8th International Conference on Learning Representations (ICLR 2020).
• Aditya Grover, Christopher Chute, Rui Shu, Zhangjie Cao, Stefano Ermon.
  AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows.
  In Proc. 34th AAAI Conference on Artificial Intelligence (AAAI 2020).
• Mike Wu, Kristy Choi, Noah Goodman, Stefano Ermon.
  Generative Modeling by Estimating Gradients of the Data Distribution.
  In Proc. 34th AAAI Conference on Artificial Intelligence (AAAI 2020).

2019

• Chi-Sing Ho, Neal Jean, Catherine A. Hogan, Lena Blackmon, Stefanie S. Jeffrey, Mark Holodniy, Niaz Banaei, Amr A. E. Saleh, Stefano Ermon, Jennifer Dionne.
  Rapid Identification of Pathogenic Bacteria using Raman Spectroscopy and Deep Learning.
  In Nature Communications, 30 Oct 2019, Issue 10, Number 4927, DOI: 10.1038/s41467-019-12898-9.
• Yang Song, Stefano Ermon.
  Generative Modeling by Estimating Gradients of the Data Distribution (Oral Presentation). [Code]
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, Stefano Ermon.
  Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting.
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Yang Song, Chenlin Meng, Stefano Ermon.
  MintNet: Building Invertible Neural Networks with Masked Convolutions. [Code]
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Lantao Yu, Tianhe Yu, Chelsea Finn, Stefano Ermon.
  Meta-Inverse Reinforcement Learning with Probabilistic Context Variables. [Code]
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Jonathan Kuck, Tri Dao, Hamid Rezatofighi, Ashish Sabharwa, Stefano Ermon.
  Approximating the Permanent by Sampling from Adaptive Partitions.
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei Koh, Stefano Ermon.
  Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.
  In Proc. 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019).
• Carla Gomes, Thomas Dietterich, Christopher Barrett, Jon Conrad, Bistra Dilkina, Stefano Ermon, Fei Fang, Andrew Farnsworth, Alan Fern, Xiaoli Fern, Daniel Fink, Douglas Fisher, Alexander Flecker, Daniel Freund, Angela Fuller, John Gregoire, John Hopcroft, Steve Kelling, Zico Kolter, Warren Powell, Nicole Sintov, John Selker, Bart Selman, Daniel Sheldon, David Shmoys, Milind Tambe, Weng-Keen Wong, Christopher Wood, Xiaojian Wu, Yexiang Xue, Amulya Yadav, Abdul-Aziz Yakubu, Mary Lou Zeeman.
  Computational Sustainability: Computing for a Better World and a Sustainable Future.
  In Communications of the ACM, September 2019, Volume 62, Issue 9, pp. 56-65.
• Yang Song, Sahaj Garg, Jiaxin Shi, Stefano Ermon.
  Sliced Score Matching: A Scalable Approach to Density and Score Estimation. [Code]
  In Proc. 35th Conference on Uncertainty in Artificial Intelligence (UAI 2019), Tel Aviv, Israel.
• Jonathan Kuck, Tri Dao, Shengjia Zhao, Burak Bartan, Ashish Sabharwal, Stefano Ermon.
  Adaptive Hashing for Model Counting. [Code]
  In Proc. 35th Conference on Uncertainty in Artificial Intelligence (UAI 2019), Tel Aviv, Israel.
• Burak Uzkent, Evan Sheehan, Chenlin Meng, Zhongyi Tang, David Lobell, Marshall Burke, Stefano Ermon.
  Learning to Interpret Satellite Images using Wikipedia. [Code]
  In Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), Macau, China.
• Michael Xie, Stefano Ermon.
  Reparameterizable Subset Sampling via Continuous Relaxations. [Code]
  In Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), Macau, China.
• Evan Sheehan, Chenlin Meng, Matthew Tan, Burak Uzkent, Neal Jean, David Lobell, Marshall Burke, Stefano Ermon.
  Predicting Economic Development using Geolocated Wikipedia Articles. [Code]
  In Proc. 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019), Alaska, USA.
• Kristy Choi, Kedar Tatwawadi, Aditya Grover, Tsachy Weissman, Stefano Ermon.
  Neural Joint-Source Channel Coding. [Code]
  In Proc. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA.
• Aditya Grover, Aaron Zweig, Stefano Ermon.
  Iterative Deep Generative Modeling of Large Graphs. [Code]
  In Proc. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA.
• Lantao Yu, Jiaming Song, Stefano Ermon.
  Multi-Agent Adversarial Inverse Reinforcement Learning. [Code]
  In Proc. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA.
• Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon.
  Calibrated Model-Based Deep Reinforcement Learning. [Code]
  In Proc. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA.
• Hongyu Ren, Shengjia Zhao, Stefano Ermon.
  Adaptive Antithetic Sampling for Variance Reduction.
  In Proc. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA.
• Aditya Grover, Eric Wang, Aaron Zweig, Stefano Ermon.
  Stochastic Optimization of Sorting Networks via Continuous Relaxations. [Code]
  In Proc. 7th International Conference on Learning Representations (ICLR 2019), New Orleans.
• Jun-Ting Hsieh, Shengjia Zhao, Stephan Eismann, Lucia Mirabella, Stefano Ermon.
  Learning Neural PDE Solvers with Convergence Guarantees. [Code]
  In Proc. 7th International Conference on Learning Representations (ICLR 2019), New Orleans.
• Mike Wu, Noah Goodman, Stefano Ermon.
  Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference. [Code]
  In Proc. 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan.
• Aditya Grover, Stefano Ermon.
  Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization. [Code]
  In Proc. 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan.
• Rui Shu, Hung Bui, Jay Whang, Stefano Ermon.
  Training Variational Autoencoders with Buffered Stochastic Variational Inference.
  In Proc. 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan.
• Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, Stefano Ermon.
  Learning Controllable Fair Representations. [Code]
  In Proc. 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Okinawa, Japan.
• Wenjie Hu, Jay Harshadbhai Patel, Zoe-Alanah Robert, Paul Novosad, Samuel Asher, Zhongyi Tang, Marshall Burke, David Lobell, Stefano Ermon.
  Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery.
  In Proc. 1st AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES 2019), Honolulu.
• Yuwei Mao, Xuelong Wang, Sihao Xia, Kai Zhang, Chenxi Wei, Seongmin Bak, Zulipiya Shadike, Xuejun Liu, Yang Yang, Rong Xu, Piero Pianetta, Stefano Ermon, Eli Stavitski, Kejie Zhao, Zhengrui Xu, Feng Lin, Xiao-Qing Yang, Enyuan Hu, Yijin Liu.
  High-Voltage Charging-Induced Strain, Heterogeneity, and Micro-Cracks in Secondary Particles of a Nickel-Rich Layered Cathode Material.
  In Advanced Functional Materials, 2019, Volume 29, Issue 18, pp. 1900247.
• Jian Wei Khor, Neal Jean, Eric S Luxenberg, Stefano Ermon, Sindy K Y Tang.
  Using Machine Learning to Discover Shape Descriptors for Predicting Emulsion Stability in a Microfluidic Channel.
  In Soft Matter, 2019, Volume 15, Issue 6, pp. 1361-1372.
• Neal Jean, Sherrie Wang, Anshul Samar, George Azzari, David Lobell, Stefano Ermon.
  Tile2Vec: Unsupervised representation learning for spatially distributed data. [Code]
  In Proc. 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), Honolulu, Hawaii.
• Shengjia Zhao, Jiaming Song, Stefano Ermon.
  InfoVAE: Balancing Learning and Inference in Variational Autoencoders. [Code]
  In Proc. 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), Honolulu, Hawaii.

2018

• Shengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon.
  Bias and Generalization in Deep Generative Models: An Empirical Study. [Code]
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon.
  Multi-Agent Generative Adversarial Imitation Learning. [Code]
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Rui Shu, Hung Bui, Shengjia Zhao, Mykel Kochenderfer, Stefano Ermon.
  Amortized Inference Regularization.
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Yang Song, Rui Shu, Nate Kushman, Stefano Ermon.
  Constructing Unrestricted Adversarial Examples with Generative Models. [Code]
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Neal Jean, Michael Xie, Stefano Ermon.
  Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance. [Code]
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Aditya Grover, Tudor Achim, Stefano Ermon.
  Streamlining Variational Inference for Constraint Satisfaction Problems. [Code]
  In Proc. 32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada.
• Shengjia Zhao, Jiaming Song, Stefano Ermon.
  The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models. [Code]
  In Proc. 34th Conference on Uncertainty in Artificial Intelligence (UAI 2018), Monterey, CA, USA.
• Stephan Eissman, Daniel Levy, Rui Shu, Stefan Bartzsch, Stefano Ermon.
  Bayesian Optimization and Attribute Adjustment.
  In Proc. 34th Conference on Uncertainty in Artificial Intelligence (UAI 2018), Monterey, CA, USA.
• Barak Oshri, Annie Hu, Peter Adelson, Xiao Chen, Pascaline Dupas, Jeremy Weinstein, Marshall Burke, David Lobell, Stefano Ermon.
  Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning.
  In Proc. 24th ACM SIGKDD Conference (KDD 2018), London, United Kingdom.
• Yang Song, Jiaming Song, Stefano Ermon.
  Accelerating Natural Gradient with Higher-Order Invariance. [Code]
  In Proc. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden.
• Volodymyr Kuleshov, Nathan Fenner, Stefano Ermon.
  Accurate Uncertainties for Deep Learning Using Calibrated Regression.
  In Proc. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden.
• Manik Dhar, Aditya Grover, Stefano Ermon.
  Modeling Sparse Deviations for Compressed Sensing using Generative Models. [Code]
  In Proc. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden.
• Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon.
  Adversarial Constraint Learning for Structured Prediction. [Code]
  In Proc. 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), Stockholm, Sweden.
• Lijie Fan, Wenbing Huang, Chuang Gan, Stefano Ermon, Boqing Gong, Junzhou Huang.
  End-to-End Motion Representations Learning for Video Understanding.
  In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA.
• Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman.
  PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples.
  In Proc. 6th International Conference on Learning Representations (ICLR 2018), Vancouver, Canada.
• Rui Shu, Hirokazu Narui, Hung Bui, Stefano Ermon.
  A DIRT-T Approach to Unsupervised Domain Adaptation.
  In Proc. 6th International Conference on Learning Representations (ICLR 2018), Vancouver, Canada.
• Aditya Grover, Ramki Gummadi, Miguel Lazaro-Gredilla, Dale Schuurmans, Stefano Ermon.
  Variational Rejection Sampling.
  In Proc. 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018).
• Aditya Grover, Todor Markov, Norman Jin, Peter Attia, Nick Perkins, Bryan Cheong, Michael Chen, Zi Yang, Stephen Harris, William Chueh, Stefano Ermon.
  Best Arm Identification in Multi-Armed Bandits with Delayed and Partial Feedback.
  In Proc. 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018).
• Aditya Grover, Manik Dhar, Stefano Ermon.
  Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models.
  In Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA.
• Aditya Grover, Stefano Ermon.
  Boosted Generative Models.
  In Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA.
• Jonathan Kuck, Stefano Ermon.
  Approximate Inference via Weighted Rademacher Complexity.
  In Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA.
• Daniel Levy, Stefano Ermon.
  Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces.
  In Proc. 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans, USA.
• Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon.
  Learning with weak supervision from physics and data-driven constraints.
  In AI Magazine, Spring 2018, Volume 39, Issue 1, pp. 27-38.