Fan Chen

Preprints and Publications

• Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie (2025). Preprint. [arxiv]

• Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Yurun Yuan, Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie (2025). Preprint. [arxiv]

• Near-Optimal Private Learning in Linear Contextual Bandits 

Fan Chen, Jiachun Li, Alexander Rakhlin, David Simchi-Levi (2025). Preprint. [arxiv]

• Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy 

Fan Chen, Alexander Rakhlin (2025). CoLT 2025. [arxiv]

• Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
  
  Fan Chen, Dylan J. Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu (2024). NeurIPS 2024 (Spotlight). [arxiv]

• Near-Optimal Learning and Planning in Separated Latent MDPs
  
  Fan Chen, Constantinos Daskalakis, Noah Golowich, Alexander Rakhlin (2024). CoLT 2024.

• On the Optimal Lower and Upper Complexity Bounds for a Class of Composite Optimization Problem
  
  Zhenyuan Zhu, Fan Chen, Junyu Zhang, Zaiwen Wen (2023). In submission.
  
  

• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
  
  Yu Bai, Fan Chen, Huan Wang, Caiming Xiong, Song Mei (2023). NeurIPS 2023 (Oral). [Code]
  
  

• Lower Bounds for Learning in Revealing POMDPs
  
  Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai (2023). ICML 2023.

• A Unified Primal-Dual Algorithm Framework for Inequality Constrained Problems
  
  Zhenyuan Zhu, Fan Chen, Junyu Zhang, Zaiwen Wen (2022). Journal of Scientific Computing.

• Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
  
  Fan Chen, Song Mei, Yu Bai (2022). ICLR 2023 (Spotlight).
  
  

• Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
  
  Fan Chen, Song Mei, Yu Bai (2022). Annals of Statistics. [arxiv] [RL Seminar]
  
  

• A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP
  
  Fan Chen, Junyu Zhang, Zaiwen Wen (2022). NeurIPS 2022.
  
  

• Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization
  
  Shicong Cen, Fan Chen, Yuejie Chi (2022). CDC 2022.