Sequential Batch Learning in Finite-Action Linear Contextual Bandits
Operations Research, to appear.
arXivto appear
About Me
I am a Research Assistant Professor in the Department of Mathematics at HKUST. My research centers on online learning and optimization. I study sequential decision-making problems, including bandits and auctions, as well as optimization on Riemannian manifolds.
I received my Ph.D. in Machine Learning from Georgia Tech, advised by Jacob Abernethy. Previously, I obtained my master's degree from Shanghai Jiao Tong University and my bachelor's degree from Huazhong University of Science and Technology.
Research Interests
- Operations research and online decision making
- Machine learning theory and bandit algorithms
- Riemannian optimization
Publications
Learning to Bid in Non-Stationary Repeated First-Price Auctions
Operations Research, Minor Revision.
arXivMinor Revision
Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods
Mathematical Programming, Series B, 2025.
Extragradient Type Methods for Riemannian Variational Inequality Problems
International Conference on Artificial Intelligence and Statistics (AISTATS) 2024.
On Riemannian Projection-free Online Learning
Conference on Neural Information Processing Systems (NeurIPS) 2023.
Faster Margin Maximization Rates for Generic Optimization Methods
Conference on Neural Information Processing Systems (NeurIPS) 2023 (Spotlight).
arXivSpotlight
Minimizing Dynamic Regret on Geodesic Metric Spaces
Annual Conference on Learning Theory (COLT) 2023.
Adaptive Oracle-Efficient Online Learning
Conference on Neural Information Processing Systems (NeurIPS) 2022.
Bayesian Supervised Hashing
Conference on Computer Vision and Pattern Recognition (CVPR) 2017. (Spotlight, 8%).
PaperSpotlight
Multiple Instance Subspace Learning via Partial Random Projection Tree for Local Reflection Symmetry in Natural Images
Pattern Recognition (PR 2016)
Preprints
Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
Preprint, arXiv:2607.02891, 2026.
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
Preprint, arXiv:2605.09448, 2026.
Research Funding
Adaptive Learning for Online Ad Display in Non-stationary Environments
Principal Investigator · Hong Kong Research Grants Council
General Research Fund (GRF), Project No. 16506225
HKD 828,792 · October 2025–September 2028
Education
- Georgia Institute of TechnologyPh.D. in Machine Learning, 2023
- Shanghai Jiao Tong UniversityM.S. in Computer Science, 2018
- Huazhong University of Science and TechnologyBSEE in Telecommunications, 2015
Academic Service
Journal reviewer: Mathematics of Operations Research (MOR); IEEE Transactions on Automatic Control (TAC).
Conference reviewer: NeurIPS, ICML, COLT, ALT, and AISTATS.
Honors & Awards
- National Scholarship, Shanghai Jiao Tong University, 2017
- Student Travel Scholarship, CVPR, 2017
- Two Sigma Financial Modeling Challenge, Kaggle — top 7.15%, 2017
- First Prize, China Post-Graduate Mathematical Contest in Modeling, 2016
- Academic Excellence Scholarship (first-class), Shanghai Jiao Tong University, 2016
Based on Minimal Light