Chi Jin

Most-cited papers

Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition
Rong Ge, Furong Huang, Chi Jin, Yang Yuan
2015Annual Conference Computational Learning Theory1,163 citations
Semantic Scholar
How to Escape Saddle Points Efficiently
Chi Jin, Rong Ge, Praneeth Netrapalli, S. Kakade +1 more
2017International Conference on Machine Learning964 citations
Semantic Scholar
Is Q-learning Provably Efficient?
Chi Jin, Zeyuan Allen-Zhu, Sébastien Bubeck, Michael I. Jordan
2018Neural Information Processing Systems946 citations
Semantic Scholar
Provably Efficient Reinforcement Learning with Linear Function Approximation
Chi Jin, Zhuoran Yang, Zhao-Ran Wang, Michael I. Jordan
2019Annual Conference Computational Learning Theory718 citations Open access
Semantic Scholar
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
Tian-Yi Lin, Chi Jin, Michael I. Jordan
2019International Conference on Machine Learning643 citations
Semantic Scholar
No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
Rong Ge, Chi Jin, Yi Zheng
2017International Conference on Machine Learning495 citations
Semantic Scholar
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
Chi Jin, Praneeth Netrapalli, Michael I. Jordan
2019International Conference on Machine Learning404 citations
Semantic Scholar
Near-Optimal Algorithms for Minimax Optimization
Tian-Yi Lin, Chi Jin, Michael I. Jordan
2020Annual Conference Computational Learning Theory311 citations
Semantic Scholar
Provably Efficient Exploration in Policy Optimization
Qi Cai, Zhuoran Yang, Chi Jin, Zhao-Ran Wang
2019International Conference on Machine Learning310 citations
Semantic Scholar
Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
Chi Jin, Praneeth Netrapalli, Michael I. Jordan
2017Annual Conference Computational Learning Theory299 citations
Semantic Scholar
On the Theory of Transfer Learning: The Importance of Task Diversity
Nilesh Tripuraneni, Michael I. Jordan, Chi Jin
2020Neural Information Processing Systems270 citations
Semantic Scholar
Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms
Chi Jin, Qinghua Liu, Sobhan Miryoosefi
2021Neural Information Processing Systems266 citations
Semantic Scholar
Gradient Descent Can Take Exponential Time to Escape Saddle Points
S. Du, Chi Jin, J. Lee, Michael I. Jordan +2 more
2017Neural Information Processing Systems266 citations
Semantic Scholar
Reward-Free Exploration for Reinforcement Learning
Chi Jin, A. Krishnamurthy, Max Simchowitz, Tiancheng Yu
2020International Conference on Machine Learning246 citations
Semantic Scholar
Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni, Chi Jin, Michael I. Jordan
2020International Conference on Machine Learning240 citations
Semantic Scholar
Sampling can be faster than optimization
Yian Ma, Yi-An Ma, Yuan-Si Chen, Chi Jin +2 more
2018Proceedings of the National Academy of Sciences of the United States of America209 citations Open access
Semantic Scholar
On Nonconvex Optimization for Machine Learning
Chi Jin, Praneeth Netrapalli, Rong Ge, S. Kakade +1 more
2019Journal of the ACM207 citations Open access
Semantic Scholar
Stochastic Cubic Regularization for Fast Nonconvex Optimization
Nilesh Tripuraneni, Mitchell Stern, Chi Jin, Jeffrey Regier +1 more
2017Neural Information Processing Systems199 citations
Semantic Scholar
Understanding Domain Randomization for Sim-to-real Transfer
Xiaoyu Chen, Jiachen Hu, Chi Jin, Lihong Li +1 more
2021International Conference on Learning Representations183 citations
Semantic Scholar
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Yu Bai, Chi Jin
2020International Conference on Machine Learning182 citations
Semantic Scholar
A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
Chi Jin, Praneeth Netrapalli, Rong Ge, S. Kakade +1 more
2019arXiv.org169 citations
Semantic Scholar
V-Learning - A Simple, Efficient, Decentralized Algorithm for Multiagent RL
Chi Jin, Qinghua Liu, Yuanhao Wang, Tiancheng Yu
2021arXiv.org152 citations
Semantic Scholar
Near-Optimal Reinforcement Learning with Self-Play
Yunru Bai, Chi Jin, Tiancheng Yu
2020Neural Information Processing Systems150 citations
Semantic Scholar
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
Qinghua Liu, Tiancheng Yu, Yu Bai, Chi Jin
2020International Conference on Machine Learning147 citations
Semantic Scholar
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences
Chi Jin, Yu-Chen Zhang, Sivaraman Balakrishnan, M. Wainwright +1 more
2016Neural Information Processing Systems147 citations
Semantic Scholar
Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm
Prateek Jain, Chi Jin, S. Kakade, Praneeth Netrapalli +1 more
2016Annual Conference Computational Learning Theory143 citations
Semantic Scholar
When Is Partially Observable Reinforcement Learning Not Scary?
Qinghua Liu, A. Chung, Csaba Szepesvari, Chi Jin
2022Annual Conference Computational Learning Theory138 citations Open access
Semantic Scholar
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
Chi Jin, Tiancheng Jin, Hai-Peng Luo, Suvrit Sra +1 more
2019International Conference on Machine Learning124 citations
Semantic Scholar
Is RLHF More Difficult than Standard RL?
Yuanhao Wang, Qinghua Liu, Chi Jin
2023Neural Information Processing Systems112 citations Open access
Semantic Scholar
Stability and Convergence Trade-off of Iterative Optimization Algorithms
Yuan-Si Chen, Chi Jin, Bin Yu
2018arXiv.org107 citations
Semantic Scholar
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, S. Kakade, A. Krishnamurthy, Qinghua Liu
2020Neural Information Processing Systems88 citations
Semantic Scholar
Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal
Chi Jin, Praneeth Netrapalli, Michael I. Jordan
2019arXiv.org87 citations
Semantic Scholar
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent
Chi Jin, S. Kakade, Praneeth Netrapalli
2016Neural Information Processing Systems87 citations
Semantic Scholar
Faster Eigenvector Computation via Shift-and-Invert Preconditioning
D. Garber, Elad Hazan, Chi Jin, S. Kakade +3 more
2016International Conference on Machine Learning84 citations
Semantic Scholar
Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis
Rong Ge, Chi Jin, S. Kakade, Praneeth Netrapalli +1 more
2016International Conference on Machine Learning83 citations
Semantic Scholar
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
Yu Bai, Chi Jin, Haiquan Wang, Caiming Xiong
2021Neural Information Processing Systems82 citations
Semantic Scholar
Stochastic Gradient Descent Escapes Saddle Points Efficiently
Chi Jin, Praneeth Netrapalli, Rong Ge, S. Kakade +1 more
2019arXiv.org64 citations
Semantic Scholar
Near-optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu, Xiao-Yu Chen, Chi Jin, Lihong Li +1 more
2021International Conference on Machine Learning63 citations
Semantic Scholar
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
Chi Jin, Qinghua Liu, Tiancheng Yu
2021International Conference on Machine Learning61 citations
Semantic Scholar
On the Local Minima of the Empirical Risk
Chi Jin, Lydia T. Liu, Rong Ge, Michael I. Jordan
2018Neural Information Processing Systems61 citations
Semantic Scholar
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Yaqi Duan, Chi Jin, Zhiyuan Li
2021International Conference on Machine Learning58 citations
Semantic Scholar
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network
Mo Zhou, Rong Ge, Chi Jin
2021Annual Conference Computational Learning Theory58 citations
Semantic Scholar
Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making
Qinghua Liu, Praneeth Netrapalli, Csaba Szepesvari, Chi Jin
2023Symposium on the Theory of Computing55 citations Open access
Semantic Scholar
Provable Reinforcement Learning with a Short-Term Memory
Yonathan Efroni, Chi Jin, A. Krishnamurthy, Sobhan Miryoosefi
2022International Conference on Machine Learning51 citations
Semantic Scholar
DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Ahmed Khaled, Konstantin Mishchenko, Chi Jin
2023Neural Information Processing Systems50 citations Open access
Semantic Scholar
Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations
Zhuoran Yang, Chi Jin, Zhao-Ran Wang, Mengdi Wang +1 more
2020Neural Information Processing Systems47 citations
Semantic Scholar
Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation
Yuanhao Wang, Qinghua Liu, Yunru Bai, Chi Jin
2023Annual Conference Computational Learning Theory44 citations Open access
Semantic Scholar
Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation
Chi Jin, S. Kakade, Cameron Musco, Praneeth Netrapalli +1 more
2015arXiv.org44 citations
Semantic Scholar
Sample-Efficient Reinforcement Learning of Partially Observable Markov Games
Qinghua Liu, Csaba Szepesvari, Chi Jin
2022Neural Information Processing Systems43 citations Open access
Semantic Scholar
A Simple Reward-free Approach to Constrained Reinforcement Learning
Sobhan Miryoosefi, Chi Jin
2021International Conference on Machine Learning40 citations
Semantic Scholar