Simon Du

Anytime Acceleration of Gradient Descent COLT 2025 An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models ACL 2024 Reflect-RL: Two-Player Online RL Fine-Tuning for LMs ACL 2024 Blessing of Class Diversity in Pre-training AISTATS 2023 Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation COLT 2023 Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron COLT 2023 Active Multi-Task Representation Learning ICML 2022 Denoised MDPs: Learning World Models Better Than the World Itself ICML 2022 First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach ICML 2022 Gap-Dependent Bounds for Two-Player Markov Games AISTATS 2022 Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies COLT 2022 Nearly Optimal Policy Optimization with Stable at Any Time Guarantee ICML 2022 Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path ICML 2022 Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games AISTATS 2022 Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes ICML 2022 Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021 Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap COLT 2021 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning ICML 2021 Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon COLT 2021 Near Optimal Reward-Free Reinforcement Learning ICML 2021 On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP ICML 2021 Q-learning with Logarithmic Regret AISTATS 2021 Provable Representation Learning for Imitation Learning via Bi-level Optimization ICML 2020 Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks ICML 2019 Gradient Descent Finds Global Minima of Deep Neural Networks ICML 2019 Provably efficient RL with Rich Observations via Latent State Decoding ICML 2019 Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019 Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms ICML 2018 Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow ICML 2018 Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima ICML 2018 On the Power of Over-parametrization in Neural Networks with Quadratic Activation ICML 2018 Stochastic Zeroth-order Optimization in High Dimensions AISTATS 2018 Spectral Gap Error Bounds for Improving CUR Matrix Decomposition and the Nyström Method AISTATS 2015