Sotabase

Career

· Assistant Professor, Machine Learning Department, Carnegie Mellon University2024–
· Postdoctoral Researcher in Robot Locomotion Group, MIT CSAIL2021–

Publications (68)

Gradient Descent Only Converges to Minimizers
Annual Conference Computational Learning Theory · 2016
622
cited
Delayed Impact of Fair Machine Learning
International Conference on Machine Learning · 2018
507
cited
Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
International Conference on Machine Learning · 2015
400
cited
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
Annual Conference Computational Learning Theory · 2018
362
cited
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Neural Information Processing Systems · 2024
319
cited
First-order methods almost always avoid strict saddle points
Mathematical programming · 2019
214
cited
Gradient Descent Converges to Minimizers
arXiv.org · 2016
214
cited
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Neural Information Processing Systems · 2019
162
cited
Diffusion Policy Policy Optimization
International Conference on Learning Representations · 2024
142
cited
Learning Linear Dynamical Systems with Semi-Parametric Least Squares
Annual Conference Computational Learning Theory · 2019
124
cited
Do Differentiable Simulators Give Better Policy Gradients?
International Conference on Machine Learning · 2022
118
cited
First-order methods almost always avoid saddle points: The case of vanishing step-sizes
Neural Information Processing Systems · 2019
115
cited
The Implicit Fairness Criterion of Unconstrained Learning
International Conference on Machine Learning · 2018
95
cited
First-order Methods Almost Always Avoid Saddle Points
arXiv.org · 2017
84
cited
History-Guided Video Diffusion
International Conference on Machine Learning · 2025
73
cited
The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime
Annual Conference Computational Learning Theory · 2017
67
cited
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
International Conference on Machine Learning · 2022
57
cited
Stabilizing Dynamical Systems via Policy Gradient Methods
Neural Information Processing Systems · 2021
49
cited
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
International Conference on Machine Learning · 2021
48
cited
Approximate Ranking from Pairwise Comparisons
International Conference on Artificial Intelligence and Statistics · 2018
45
cited
Sotabase
Max Simchowitz | Researcher Profile | Sotabase | Sotabase