Reinforcement learning and sequential decision-making

Deep Transfer Q-Learning for Offline Non-Stationary Reinforcement Learning
With Elynn Chen, Jianqing Fan
Preprint, 2025. arXiv

Transition Transfer Q-Learning for Composite Markov Decision Processes
With Elynn Chen, Lin Yang
ICML 2025; arXiv

Localized exploration in contextual dynamic pricing achieves dimension-free regret
With Yaqi Duan, Jianqing Fan, Kaizheng Wang
Preprint, 2024. arXiv

Optimal Semiparametric Dynamic Pricing with Feature Diversity
With Yaqi Duan, Jianqing Fan, Kaizheng Wang
Preprint, 2026. arXiv

Optimistic Transfer under Task Shift via Bellman Alignment
With Enpei Zhang, Elynn Chen, Yujun Yan
Preprint, 2026. arXiv

Statistical Learning Theory

Structured Matrix Learning under Arbitrary Entrywise Dependence and Estimation of Markov Transition Kernel
With Jianqing Fan
The Annals of Statistics, 53(5):1938-1962 (2025); arXiv

Neural Distribution Regression
With Jianqing Fan, Yihong Gu
Preprint, 2026. arXiv

Transfer Learning

SMART Fine-tuning Factor Augmented Neural Lasso
With Jianqing Fan, Cheng Gao, Qishuo Yin
Preprint, 2026. arXiv

Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensions
With Xuyuan Liu, Elynn Chen, Yujun Yan
Preprint, 2026. arXiv