Jacob Steinhardt (jsteinhardt@cs)

I am a third-year graduate student in artificial intelligence at Stanford University working with Percy Liang. I have previously worked with Russ Tedrake, Zoubin Ghahramani, and Josh Tenenbaum.

My primary technical interest is learning with approximate inference: how can we learn statistical models when inference is intractable? I am also interested in online learning, especially under resource constraints such as memory or communication limits.

More broadly, I am interested in what tools and concepts we need to build human-level artificial intelligences. I believe that computationally-bounded reasoning is a crucial step along this path, which is what motivates my current technical interests. Along these lines, I am also interested in how to build (or learn) useful formal specifications for machine learning systems.

Outside of research, I am a coach for the USA Computing Olympiad and an instructor at the Summer Program in Applied Rationality and Cognition. I also consult part-time for GiveWell. I like indoor bouldering and ultimate frisbee.


I maintain two blogs, an expository blog as well as a daily research log (somewhat out of date).
I've also written some about Bayesian and frequentist statistics.
Most recently, I've written an essay on research challenges in ensuring the safety of AI systems.


Learning with Memory and Communication Constraints
Learning with Intractable Inference and Partial Supervision


(asterisk indicates joint or alphabetical authorship)

Jacob Steinhardt and Percy Liang
Learning with Relaxed Supervision
NIPS 2015
[Paper] [Code] [Poster]

Jacob Steinhardt*, Gregory Valiant*, and Stefan Wager*
Memory, Communication, and Statistical Queries
ECCC preprint

Jacob Steinhardt and Percy Liang
Reified Context Models
ICML 2015
[Paper] [Code] [Slides] [Poster]

Jacob Steinhardt and Percy Liang
Learning Fast-Mixing Models for Structured Prediction
ICML 2015
[Paper] [Code] [Slides] [Talk] [Poster]

Jacob Steinhardt and John Duchi
Minimax Rates for Memory-Constrained Sparse Linear Regression
COLT 2015
[Paper] [Slides] [Talk] [Poster]

Tianlin Shi, Jacob Steinhardt, and Percy Liang
Learning Where to Sample in Structured Prediction
[Paper] [Code: GitHub/CodaLab] [Slides]

Jacob Steinhardt*, Stefan Wager*, and Percy Liang
The Statistics of Streaming Sparse Regression
arXiv preprint

Jacob Steinhardt and Percy Liang
Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm
ICML 2014
[Paper] [Slides] [Poster]

Jacob Steinhardt and Percy Liang
Filtering with Abstract Particles
ICML 2014
[Paper] [Slides] [Poster]

Jacob Steinhardt and Zoubin Ghahramani
Flexible Martingale Priors for Deep Hierarchies
[Paper] [Slides] [Poster]

Jacob Steinhardt and Zoubin Ghahramani
Pathological Properties of Deep Bayesian Hierarchies
2011 NIPS Workshop on Bayesian Nonparametrics
[Poster Abstract] [Poster]

Jacob Steinhardt and Russ Tedrake
Finite-Time Regional Verification of Stochastic Nonlinear Systems
Robotics: Science and Systems, 2011
Best Student Paper Finalist
[Conference Paper and Errata] [Journal Paper] [Slides] [Poster]

Jacob Steinhardt
Permutations with Ascending and Descending Blocks
Electronic Journal of Combinatorics, 17:R14
[Paper] [Slides]

Jacob Steinhardt
On Coloring the Odd-Distance Graph
Electronic Journal of Combinatorics, 16:N12

Jacob Steinhardt
Cayley Graphs Formed by Conjugate Generating Sets of S_n
3rd Place in 2007 Siemens Competition