Chi Jin

Benign Overfitting in Out-of-Distribution Generalization of Linear Models ICLR 2025 Building Math Agents with Multi-Turn Iterative Preference Learning ICLR 2025 DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization ICCV 2025 MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations ICML 2025 PokéChamp: an Expert-level Minimax Language Agent ICML 2025 Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games ICML 2025 Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization JMLR 2025 Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning ICLR 2024 FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning ICML 2024 Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift ICLR 2024 On the Provable Advantage of Unsupervised Pretraining ICLR 2024 Tuning-Free Stochastic Optimization ICML 2024 Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation COLT 2023 Context-lumpable stochastic bandits NeurIPS 2023 DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method NeurIPS 2023 Efficient displacement convex optimization with particle gradient descent ICML 2023 Faster federated optimization under second-order similarity ICLR 2023 Is RLHF More Difficult than Standard RL? A Theoretical Perspective NeurIPS 2023 Learning Rationalizable Equilibria in Multiplayer Games ICLR 2023 Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL NeurIPS 2023 Provable Sim-to-real Transfer in Continuous Domain with Partial Observations ICLR 2023 Representation Learning for Low-rank General-sum Markov Games ICLR 2023 A Simple Reward-free Approach to Constrained Reinforcement Learning ICML 2022 Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent NeurIPS 2022 Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits ICML 2022 Minimax Optimization with Smooth Algorithmic Adversaries ICLR 2022 Near-Optimal Learning of Extensive-Form Games with Imperfect Information ICML 2022 Provable Reinforcement Learning with a Short-Term Memory ICML 2022 Sample-Efficient Reinforcement Learning of Partially Observable Markov Games NeurIPS 2022 The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces ICML 2022 Understanding Domain Randomization for Sim-to-real Transfer ICLR 2022 When Is Partially Observable Reinforcement Learning Not Scary? COLT 2022 A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network COLT 2021 A Sharp Analysis of Model-based Reinforcement Learning with Self-Play ICML 2021 Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms NeurIPS 2021 Near-Optimal Representation Learning for Linear Bandits and Linear RL ICML 2021 Provable Meta-Learning of Linear Representations ICML 2021 Provable Rich Observation Reinforcement Learning with Combinatorial Latent States ICLR 2021 Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning ICML 2021 Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games NeurIPS 2021 Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition ICML 2020 Near-Optimal Algorithms for Minimax Optimization COLT 2020 Near-Optimal Reinforcement Learning with Self-Play NeurIPS 2020 On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems ICML 2020 On the Theory of Transfer Learning: The Importance of Task Diversity NeurIPS 2020 Provable Self-Play Algorithms for Competitive Reinforcement Learning ICML 2020 Provably Efficient Exploration in Policy Optimization ICML 2020 Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations NeurIPS 2020 Provably efficient reinforcement learning with linear function approximation COLT 2020 Reward-Free Exploration for Reinforcement Learning ICML 2020 Sample-Efficient Reinforcement Learning of Undercomplete POMDPs NeurIPS 2020 What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? ICML 2020 Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent COLT 2018 Is Q-Learning Provably Efficient? NeurIPS 2018 On the Local Minima of the Empirical Risk NeurIPS 2018 Stochastic Cubic Regularization for Fast Nonconvex Optimization NeurIPS 2018 Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot AISTATS 2017 Gradient Descent Can Take Exponential Time to Escape Saddle Points NeurIPS 2017 How to Escape Saddle Points Efficiently ICML 2017 No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis ICML 2017 Differentially Private Data Releasing for Smooth Queries JMLR 2016 Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis ICML 2016 Faster Eigenvector Computation via Shift-and-Invert Preconditioning ICML 2016 Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences NeurIPS 2016 Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent NeurIPS 2016 Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja’s Algorithm COLT 2016 Escaping From Saddle Points — Online Stochastic Gradient for Tensor Decomposition COLT 2015 Dimensionality Dependent PAC-Bayes Margin Bound NeurIPS 2012