Awards and honors

• [2015] Gold medal in 56th International Mathematical Olympiad

• [2023] Amazon Science Hub Fellowship

• [2024] Dissertation Year Award in University of California, Los Angeles

Conference Publications

• Achieving Constant Regret in Linear Markov Decision Processes

Weitong Zhang, Zhiyuan Fan, Jiafan He, Quanquan Gu

Neural Information Processing Systems (NeurIPS), 2024

• A nearly optimal and low-switching algorithm for reinforcement learning with general function approximation

Heyang Zhao, Jiafan He, Quanquan Gu

Neural Information Processing Systems (NeurIPS), 2024

• Towards robust model-based reinforcement learning against adversarial corruption

Chenlu Ye, Jiafan He, Quanquan Gu, Tong Zhang 

International Conference on Machine Learning (ICML), 2024

• Pessimistic nonlinear least-squares value iteration for offline reinforcement learning

Qiwei Di, Heyang Zhao, Jiafan He, Quanquan Gu

International Conference on Learning Representations (ICLR), 2024

• Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs 

Kaixuan Ji, Qingyue Zhao, Jiafan He, Weitong Zhang, Quanquan Gu 

International Conference on Learning Representations (ICLR), 2024

• Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency

Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu.

Conference on Learning Theory (COLT), 2023

• Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL

Weitong Zhang, Jiafan He, Dongruo Zhou, Amy Zhang, Quanquan Gu

Uncertainty in Artificial Intelligence (UAI), 2023

• Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension

Yue Wu, Jiafan He, Quanquan Gu

Uncertainty in Artificial Intelligence (UAI), 2023

• Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu

International Conference on Machine Learning (ICML), 2023

• Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes

Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu

International Conference on Machine Learning (ICML), 2023

• On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

Weitong Zhang, Jiafan He, Zhiyuan Fan, Quanquan Gu

International Conference on Machine Learning (ICML), 2023

• Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits

Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu

International Conference on Machine Learning (ICML), 2023

• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path  

Qiwei Di, Jiafan He, Dongruo Zhou, Quanquan Gu

International Conference on Machine Learning (ICML), 2023

• A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Jiafan He, Tianhao Wang, Yifei Min, Quanquan Gu

Neural Information Processing Systems (NeurIPS), 2022 

• Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Jiafan He,  Dongruo Zhou, Tong Zhang, Quanquan Gu

Neural Information Processing Systems (NeurIPS), 2022 

• Locally Differentially Private Reinforcement Learning for Linear Mixture MDPs 

Chonghua Liao, Jiafan He, Quanquan Gu

Asian Conference on Machine Learning (ACML), 2022 

• On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs

Yuanzhou Chen, Jiafan He, Quanquan Gu 

International Conference on Machine Learning (ICML), 2022 

• Learning Stochastic Shortest Path with Linear Function Approximation

Yifei Min, Jiafan He, Tiaohao Wang, Quanquan Gu 

International Conference on Machine Learning (ICML), 2022 

• Nearly Optimal Regret for Learning Adversarial MDPs with Linear Function Approximation 

Jiafan He, Dongruo Zhou, Quanquan Gu. 

International Conference on Artificial Intelligence and Statistics (AISTATS), 2022  

• Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation 

Jiafan He, Dongruo Zhou, Quanquan Gu. 

Neural Information Processing Systems (NeurIPS), 2021 

• Minimax Optimal Reinforcement Learning for Discounted MDPs  

Jiafan He, Dongruo Zhou, Quanquan Gu. 

Neural Information Processing Systems (NeurIPS), 2021 

• Logarithmic Regret for Reinforcement Learning with Linear Function Approximation 

Jiafan He, Dongruo Zhou, Quanquan Gu. 

International Conference on Machine Learning (ICML), 2021

• Provably efficient reinforcement learning for discounted MDPs with feature mapping  

Dongruo Zhou, Jiafan He, Quanquan Gu. 

International Conference on Machine Learning (ICML), 2021

• Achieving a fairer future by changing the past   

Jiafan He, Christos-Alexandros Psomas, Ariel D. Procaccia, David Zeng 

International Joint Conference on Artificial Intelligence (IJCAI), 2019 

Preprints

• Accelerated Preference Optimization for Large Language Model Alignment

Jiafan He, Huizhuo Yuan, Quanquan Gu

Neural Information Processing Systems (NeurIPS), Adaptive Foundation Models Workshop 2024

• Nearly optimal algorithms for contextual dueling bandits from adversarial feedback

Qiwei Di,  Jiafan He, Quanquan Gu

• Reinforcement learning from human feedback with active queries

Kaixuan Ji, Jiafan He, Quanquan Gu