Yunbei Xu (许云贝)

Research

• Finite-Time Information-Theoretic Bounds in Queueing Control

  with Yujie Liu and Vincent Tan

  Conference version submitted. Journal version in preparation.

• 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.

  Short version in Conference on Neural Information Processing Systems (NeurIPS) 2024.

  Spotlight

  Journal version in preparation.

• Statistical Properties of Robust Satisficing

  with Zhiyi Li and Ruohan Zhan.

  International Conference on Machine Learning (ICML) 2024.

  Journal version in preparation.

• Thompson Sampling for Repeated Newsvendor

  with Weizhou Zhang, Chen Li, Hanzhang Qin, and Ruihao Zhu.

  Conference version submitted. Journal version in preparation.

• Bayesian Design Principles for Frequentist Sequential Learning

  with Assaf Zeevi.

  Journal of the ACM, 2025. Code

  Short version in International Conference on Machine Learning (ICML) 2023.

  ICML Outstanding Paper Award

  INFORMS George Nicholson Student Paper Competition, First Place

  Applied Probability Society Best Student Paper Award, Finalist

  (arXiv link is the recommended full version)

• Towards Optimal Problem Dependent Generalization Error Bounds in Statistical Learning Theory

  with Assaf Zeevi.

  Mathematics of Operations Research, 2024.

  Applied Probability Society Best Student Paper Award, Finalist

  ---

  Towards Problem-dependent Optimal Learning Rates

  with Assaf Zeevi.

  Conference on Neural Information Processing Systems (NeurIPS) 2020.

  Spotlight (top 2.9%)

• Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits

  with Assaf Zeevi.

  Major Revision at a top journal.

• Acceleration of Primal-Dual Methods by Preconditioning and Simple Subproblem Procedures

  with Yanli Liu and Wotao Yin.

  Journal of Scientific Computing, 2021. Code