← Authors

Max Simchowitz

48 papers · 2016–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (10) πŸƒ Academic Marathon (9) πŸŒ‰ Interdisciplinary Bridge 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (50) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) πŸ”¬ Deep Specialist (12) πŸ‘‘ Triple Crown πŸ† Keyword Champion (5) πŸ—ƒοΈ Keyword Collector (176) ⚑ Prolific Year (9) πŸ’Ž Century Club (48) πŸ”₯ Unstoppable (10) ❓ The Questioner

Conferences

ICML (14) COLT (13) NIPS (13) ICLR (5) AISTATS (1) IJCAI (1) RSS (1)

Top co-authors

Russ Tedrake (8) Kevin Jamieson (6) Akshay Krishnamurthy (6) Adam Block (6) Kaiqing Zhang (5) Benjamin Recht (5) Andrew J Wagenmaker (4) Moritz Hardt (4) Lydia T. Liu (4) Sarah Dean (3)

Keywords

regret bound (10) sample complexity (7) reinforcement learning (6) linear dynamical system (6) linear quadratic regulator (5) online control (4) dynamical system (3) smoothed online learning (3) gradient descent (3) online learning (3) fairness criterion (3) diffusion model (2) multi-armed bandit (2) domain generalization (2) sublinear regret (2) temporal modeling (2) policy gradient (2) distribution shift (2) pac learning (2) optimal control (2)

Papers

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