Max Simchowitz

19

Papers

132

Total Citations

Papers (19)

History-Guided Video Diffusion

Self-Improvement in Language Models: The Sharpening Mechanism

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Is Your Diffusion Model Actually Denoising?

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Online Control of Unknown Time-Varying Dynamical Systems

Bayesian decision-making under misspecified priors with applications to meta-learning

Stabilizing Dynamical Systems via Policy Gradient Methods

Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions

Globally Convergent Policy Search for Output Estimation

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Smoothed Online Learning for Prediction in Piecewise Affine Systems

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Delayed Impact of Fair Machine Learning

The Implicit Fairness Criterion of Unconstrained Learning

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

Learning the Linear Quadratic Regulator from Nonlinear Observations

Constrained episodic reinforcement learning in concave-convex and knapsack settings