Jiheng Zhang

Full Professor, The Hong Kong University of Science and Technology

Joined

May 2021

Names

Jiheng Zhang (Preferred)

Emails

****@ust.hk (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Full Professor

The Hong Kong University of Science and Technology (ust.hk)

2020 – Present

Advisors, Relations & Conflicts

PhD Advisor

Jim Dai

2003 – 2009

Expertise

learning

2018 – Present

stochastic process

2003 – Present

Publications

ONLINE RANKING WITH UNFAIR FEEDBACK AND HUMAN VERIFICATION: HIERARCHICAL ELIMINATION AND REGRET BOUNDS
Ruihan Lin, Jiheng Zhang
- Submitted to ICLR 2026
- Readers: Everyone
Make Optimization Once and for All with Fine-grained Guidance
Mingjia Shi, Ruihan Lin, Xuxi Chen, Yuhao Zhou, Mengxuan Wu, Zezhen Ding, Pingzhi Li, Tong Wang, Kai Wang, Zhangyang Wang, Jiheng Zhang, Tianlong Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
A closer look at the explainability of contrastive language-image pre-training
Yi Li, Hualiang Wang, Yiqun Duan, Jiheng Zhang, Xiaomeng Li
- Pattern Recognition
- Readers: Everyone
Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases
Chuang Zhao, Hui Tang, Jiheng Zhang, Xiaomeng Li
- WWW 2025 Oral
- Readers: Everyone
Single-Trajectory Distributionally Robust Reinforcement Learning
Zhipeng Liang, Xiaoteng Ma, Jose Blanchet, Jun Yang, Jiheng Zhang, Zhengyuan Zhou
- ICML 2024 Poster
- Readers: Everyone
Improved Regret Bounds in Stochastic Contextual Bandits with Graph Feedback
Xueping Gong, Jiheng Zhang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Single-Trajectory Distributionally Robust Reinforcement Learning
Zhipeng Liang, Xiaoteng Ma, Jose Blanchet, Jun Yang, Jiheng Zhang, Zhengyuan Zhou
- Submitted to ICLR 2024
- Readers: Everyone
Robustify the Latent Space: Offline Distributionally Robust Reinforcement Learning with Linear Function Approximation
Zhipeng Liang, Xiaoteng Ma, Jose Blanchet, Mingwen Liu, Jiheng Zhang, Zhengyuan Zhou
- Submitted to ICLR 2024
- Readers: Everyone
Provably Efficient Learning in Partially Observable Contextual Bandit
Xueping Gong, Jiheng Zhang
- Submitted to ICLR 2024
- Readers: Everyone
Single-Trajectory Distributionally Robust Reinforcement Learning
Zhipeng Liang, Xiaoteng Ma, Jose H. Blanchet, Jiheng Zhang, Zhengyuan Zhou
- 2023 (modified: 21 Apr 2023)
- CoRR 2023
- Readers: Everyone

View all 39 publications

Co-Authors

View all 62 co-authors