Publications
"α" denotes alphabetical author order, "*" denotes equal contribution (for non-alphabetical author order).
Selected Works
Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
α: Adam Block*, Ali Jadbabaie, Daniel Pfrommer*, Max Simchowitz*, Russ Tedrake. Neurips, 2023.
Former title, currently used by Google Scholar: "Imitating Complex Behavior: Bridging Low-Level Stability and High-Level Behavior"
Statistical Learning under Heterogeneous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy. ICML, 2023.
Do Differentiable Simulators Give Better Policy Gradients?
H.J. Terry Suh, Max Simchowitz, Kaiqing Zhang, Russ Tedrake. ICML, Outstanding Paper Award, 2022.
Naive Exploration is Optimal for Online LQR Max Simchowitz, Dylan Foster. ICML, 2020.
Improper Learning for Nonstochastic Control Max Simchowitz, Karan Singh, Elad Hazan. COLT, 2020.
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Max Simchowitz, Kevin Jamieson. NeurIPS, 2019.
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
Max Simchowitz, Horia Mania, Stephen Tu, Benjamin Recht, Michael I. Jordan. COLT, 2018.
PhD Thesis
Current Preprints
Refereed Publications
2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang. Under submission, 2024.
Fleet Policy Learning via Weight Merging and An Application to Robotic Tool-Use
Lirui Wang, Kaiqing Zhang, Allan Zhou, Max Simchowitz, Russ Tedrake. ICLR, 2024.
2023
Corruption Robust Exploration in Episodic Reinforcement Learning α: Thodoris Lykouris, Max Simchowitz, Aleksandrs Slivkins, Wen Sun. Mathematics of Operations Research, 2023.
Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
α: Adam Block , Daniel Pfrommer, Max Simchowitz. Neurips, 2023.
Smoothed Online Learning for Prediction in Piecewise Affine Systems
α: Adam Block, Max Simchowitz, Russ Tedrake. NeurIPS, Spotlight, 2023.
RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability
Chuning Zhu, Max Simchowitz, Siri Gadipudi, Abhishek Gupta. Neurips, Spotlight, 2023.
Imitating Complex Trajectories: Bridging Low-Level Stability and High-Level Behavior
α: Adam Block , Daniel Pfrommer, Max Simchowitz. Frontiers4LCD Workshop, ICML, 2023.
Non-Euclidean Motion Planning with Graphs of Geodesically-Convex Sets
Thomas Cohn, Mark Petersen, Max Simchowitz, Russ Tedrake. RSS, Best Paper Finalist, 2023.
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
α: Adam Block, Sasha Rakhlin, Max Simchowitz. COLT, 2023.
Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective
Max Simchowitz, Abhishek Gupta, Kaiqing Zhang. COLT, 2023.
Exploration and Incentives in Reinforcement Learning Max Simchowitz, Aleksandrs Slivkins. Operations Research, 2023 (to appear).
Statistical Learning under Heterogenous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy. ICML, 2023.
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
Daniel Pfrommer* , Max Simchowitz* , Tyler Westenbroek, Nikolai Matni, Stephen Tu. ICML, 2023.
Learning to Extrapolate: A Transductive Approach
Aviv Netanyahu, Abhishek Gupta, Max Simchowitz, Kaiqing Zhang, Pulkit Agrawal. ICLR, 2023.
2022
Pathologies and Challenges of Using Differentiable Simulators in Policy Optimization for Contact-Rich Manipulation
H.J. Terry Suh, Max Simchowitz, Kaiqing Zhang, Russ Tedrake. ICRA 2022 Workshop: Reinforcement Learning for Contact-Rich Manipulation, 2022.
Learning to Extrapolate: A Transductive Approach
Aviv Netanyahu, Abhishek Gupta, Max Simchowitz, Kaiqing Zhang, Pulkit Agrawal. NeurIPS 2022 Workshop on Distribution Shifts (DistShift), 2022.
Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions
α: Adam Block, Max Simchowitz. NeurIPS, 2022.
Globally Convergent Policy Search over Dynamic Filters for Output Estimation
Jack Umenberger*, Max Simchowitz*, Juan C. Perdomo, Kaiqing Zhang, Russ Tedrake. NeurIPS, 2022.
Do Differentiable Simulators Give Better Policy Gradients?
H.J. Terry Suh, Max Simchowitz, Kaiqing Zhang, Russ Tedrake. ICML, Outstanding Paper Award, 2022.
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson. ICML, Spotlight. 2022.
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson. ICML, Oral., 2022.
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson. COLT, 2022.
2021
Bayesian decision-making under misspecified priors with applications to meta-learning Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu,
Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire. Neurips, Spotlight, 2021.
Stabilizing Dynamical Systems via Policy Gradient Methods
Juan C. Perdomo, Jack Umenberger, Max Simchowitz. Neurips, 2021.
Online Control of Unknown Time-Varying Dynamical Systems
Edgar Minasyan, Paula Gradu, Max Simchowitz, Elad Hazan. Neurips, 2021.
On Stability of Nonlinear Receding Horizon Control: A Geometric Perspective
Tyler Westenbroek*, Max Simchowitz*, Michael I. Jordan, S. Shankar Sastry. CDC, 2021.
Task-Optimal Exploration in Linear Dynamical Systems
Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson. ICML, 2021.
Towards a Dimension-Free Understanding of Adaptive Linear Control Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter Bartlett. COLT, 2021.
α: Corruption Robust Exploration in Episodic Reinforcement Learning Thodoris Lykouris, Max Simchowitz, Aleksandrs Slivkins, Wen Sun. COLT (extended abstract), 2021.
2020
Making Non-Stochastic Control (Almost) as Easy as Stochastic
Max Simchowitz. NeurIPS, 2020.
Learning a Linear Quadratic Regular from Nonlinear
Observations Zak Mhammedi, Dylan Foster, Max Simchowitz, Dipendra Misra,
Akshay Krishnamurthy, Sasha Rakhlin, John Langford. NeurIPS, 2020.
Constrained episodic reinforcement learning in concave-convex and knapsack setting α: Kianté Brantley, Miroslav Dudik, Thodoris Lykouris, Sobhan Miryoosefi,
Max Simchowitz, Aleksandrs Slivkins, Wen Sun. NeurIPS, 2020.
Improper Learning for Nonstochastic Control Max Simchowitz, Karan Singh, Elad Hazan. COLT, 2020.
Naive Exploration is Optimal for Online LQR Max Simchowitz, Dylan Foster. ICML, 2020.
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning Esther Rolf, Max Simchowitz, Sarah Dean, Lydia T. Liu, Daniel Björkegren, Moritz Hardt, Joshua Blumenstock. ICML, 2020.
Logarithmic Regret for Online Control with Adversarial Disturbances Dylan Foster, Max Simchowitz. ICML, 2020.
Reward-Free Exploration for Reinforcement Learning α: Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu. ICML, 2020.
The gradient complexity of linear regression
α: Mark Braverman, Elad Hazan, Max Simchowitz, Blake Woodworth. COLT, 2020.
A Successive-Elimination Approach to Adaptive Robotic Source Seeking Esther Rolf, David Fridovich-Keil, Max Simchowitz, Benjamin Recht, Claire Tomlin. IEEE Transactions on Robotics, 2020.
2019
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Max Simchowitz, Kevin Jamieson. NeurIPS, 2019.
Learning Linear Dynamical Systems with Semi-Parametric Least Squares Max Simchowitz, Ross Boczar, Benjamin Recht. COLT, 2019.
The Implicit Fairness Criterion of Unconstrained Learning Lydia Liu, Max Simchowitz, Moritz Hardt. ICML, 2019.
Balancing Competing Objectives for Welfare-Aware Machine Learning with Imperfect Data. Esther Rolf, Max Simchowitz, Sarah Dean, Lydia T. Liu, Daniel Björkegren, Moritz Hardt, Joshua Blumenstock. The Neural Information Processing Systems Joint Workshop on AI for Social Good, Best Paper Award, 2019.
First-order Methods Almost Always Avoid Saddle Points
Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht. Mathematical Programming (pg. 1-27), 2019.
2018
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
Max Simchowitz, Horia Mania, Stephen Tu, Benjamin Recht, Michael I. Jordan. COLT, 2018.
Delayed Impact of Fair Machine Learning
Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt. ICML, Best Paper Award 2018.
Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law
Max Simchowitz, Ahmed El Alaoui, Benjamin Recht. STOC, 2018.
Approximate Ranking from Pairwise Comparisons
Reinhard Heckel, Max Simchowitz, Kannan Ramchandran, Martin J. Wainwright. AISTATS, 2018.
2017
The Simulator: Towards a Richer Understanding of Adaptive Sampling in the Moderate-Confidence Regime
Max Simchowitz, Kevin Jamieson, and Benjamin Recht. COLT, 2017.
2016
Best-of-K Bandits
Max Simchowitz, Kevin Jamieson, and Benjamin Recht. COLT, 2016.
Gradient Descent Converges to Minimizers.
Jason D. Lee, Max Simchowitz, Michael I. Jordan, and Benjamin Recht. COLT, 2016.
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow.
Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, Benjamin Recht. ICML, 2016.
Older Writing
Miscellaneous Preprints
On the Randomized Complexity of Minimizing a Convex Quadratic Function Max Simchowitz. 2018.
On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
Max Simchowitz, Ahmed El Alaoui, Benjamin Recht . 2017.
Undergraduate Projects
Dictionary Learning and Anti-Concentration
Max Simchowitz
Undergraduate Senior Thesis, advised by Sanjeev Arora, Princeton University, Spring 2015 .
Notes on Probability Theory, Random Matrices, and the Marchenko Pastur Law
Max Simchowitz
Notes for High Dimensional Statistics Junior Seminar, taught by Amit Singer, Princeton University, Spring 2014.
Authorship Detection using Supervised Topic Models (github)
David Dohan, Charles Marsh, Shubhro Saha, Max Simchowitz.
Class Project for Princeton COS 424 (Interacting with Data), taught by David Blei, Princeton University, Spring 2014.
Zero-Inflated Poisson for Recommendation
Max Simchowitz
Junior Independent Work, Fall 2013. Advised by David Blei
|