Max Simchowitz

Diffusion Policy Policy Optimization ICLR 2025 History-Guided Video Diffusion ICML 2025 Self-Improvement in Language Models: The Sharpening Mechanism ICLR 2025 The Pitfalls of Imitation Learning when Actions are Continuous COLT 2025 Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024 Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion NeurIPS 2024 Robot Fleet Learning via Policy Merging ICLR 2024 Learning to Extrapolate: A Transductive Approach ICLR 2023 Non-Euclidean Motion Planning with Graphs of Geodesically-Convex Sets RSS 2023 Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making COLT 2023 Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior NeurIPS 2023 RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability NeurIPS 2023 Smoothed Online Learning for Prediction in Piecewise Affine Systems NeurIPS 2023 Statistical Learning under Heterogeneous Distribution Shift ICML 2023 Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective COLT 2023 The Power of Learned Locally Linear Models for Nonlinear Policy Optimization ICML 2023 Beyond No Regret: Instance-Dependent PAC Reinforcement Learning COLT 2022 Do Differentiable Simulators Give Better Policy Gradients? ICML 2022 Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions NeurIPS 2022 First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach ICML 2022 Globally Convergent Policy Search for Output Estimation NeurIPS 2022 Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes ICML 2022 Bayesian decision-making under misspecified priors with applications to meta-learning NeurIPS 2021 Corruption-robust exploration in episodic reinforcement learning COLT 2021 Online Control of Unknown Time-Varying Dynamical Systems NeurIPS 2021 Stabilizing Dynamical Systems via Policy Gradient Methods NeurIPS 2021 Task-Optimal Exploration in Linear Dynamical Systems ICML 2021 Towards a Dimension-Free Understanding of Adaptive Linear Control COLT 2021 Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning ICML 2020 Constrained episodic reinforcement learning in concave-convex and knapsack settings NeurIPS 2020 Improper Learning for Non-Stochastic Control COLT 2020 Learning the Linear Quadratic Regulator from Nonlinear Observations NeurIPS 2020 Logarithmic Regret for Adversarial Online Control ICML 2020 Making Non-Stochastic Control (Almost) as Easy as Stochastic NeurIPS 2020 Naive Exploration is Optimal for Online LQR ICML 2020 Reward-Free Exploration for Reinforcement Learning ICML 2020 The Gradient Complexity of Linear Regression COLT 2020 Delayed Impact of Fair Machine Learning IJCAI 2019 Learning Linear Dynamical Systems with Semi-Parametric Least Squares COLT 2019 Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs NeurIPS 2019 The Implicit Fairness Criterion of Unconstrained Learning ICML 2019 Approximate Ranking from Pairwise Comparisons AISTATS 2018 Delayed Impact of Fair Machine Learning ICML 2018 Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification COLT 2018 The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime COLT 2017 Best-of-K-bandits COLT 2016 Gradient Descent Only Converges to Minimizers COLT 2016 Low-rank Solutions of Linear Matrix Equations via Procrustes Flow ICML 2016