Yunbei Xu
Scholar

Yunbei Xu

Google Scholar ID: j_auqHkAAAAJ
Assistant Professor, National University of Singapore
Artificial IntelligenceDecision ScienceMathematical Physics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
169
 
H-index
6
 
i10-index
4
 
Publications
11
 
Co-authors
0
 
Contact
Emailyunbei@nus.edu.sgGitHubOpen ↗
Publications
12 items
Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime
2026
Cited
0
Statistical Properties of Robust Learning under Distributional Shifts
2026
Cited
0
The Dimension of Nonterminating Resampling Computations
2026
Cited
0
Algorithmic and Minimax Complexities in Kernel Bandits
2026
Cited
0
Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation
2026
Cited
0
Pointwise Generalization in Deep Neural Networks
2026
Cited
0
On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits
2026
Cited
0
In-Context Learning for Data-Driven Censored Inventory Control
2026
Cited
0
Resume
Academic Achievements
  • - NeurIPS 2024 Spotlight paper (top 2.5%)
  • - ICML 2024 paper
  • - ICML 2023 Outstanding Paper Award
  • - INFORMS George Nicholson Student Paper Competition, First Place
  • - Applied Probability Society Best Student Paper Award, Finalist
  • - Mathematics of Operations Research paper
  • - NeurIPS 2020 Spotlight paper (top 2.9%)
  • - Journal of Scientific Computing paper
Research Experience
  • - Research project: Pointwise Generalization in Deep Neural Networks (with Shaojie Li)
  • - Research project: Finite-Time Information-Theoretic Bounds in Queueing Control (with Yujie Liu and Vincent Tan)
  • - Research project: Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability (with Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, and Alexander Rakhlin)
  • - Research project: Statistical Properties of Robust Satisficing (with Zhiyi Li and Ruohan Zhan)
  • - Research project: Thompson Sampling for Repeated Newsvendor (with Weizhou Zhang, Chen Li, Hanzhang Qin, and Ruihao Zhu)
  • - Research project: Bayesian Design Principles for Frequentist Sequential Learning (with Assaf Zeevi)
  • - Research project: Towards Optimal Problem Dependent Generalization Error Bounds in Statistical Learning Theory (with Assaf Zeevi)
  • - Research project: Towards Problem-dependent Optimal Learning Rates (with Assaf Zeevi)
  • - Research project: Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits (with Assaf Zeevi)
  • - Research project: Acceleration of Primal-Dual Methods by Preconditioning and Simple Subproblem Procedures (with Yanli Liu and Wotao Yin)
Education
  • - Postdoc, Massachusetts Institute of Technology, College of Computing, LIDS, Advisor: Sasha Rakhlin
  • - Doctor of Philosophy, Columbia University, Graduate School of Business, DRO, Advisor: Assaf Zeevi
  • - Bachelor of Science, Peking University, Department of Pure Mathematics, with highest honor
Background
  • Research interests span Artificial Intelligence, Decision Science, and Physics, using mathematics to deepen our understanding and drive positive change in the world.
Miscellany
  • Looking for motivated PhD Students and Postdocs to join his research group.