Yunbei Xu (许云贝)

Research

• Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability

  with Fan Chen, Dylan J 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.

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

  ICML Outstanding Paper Award

  INFORMS George Nicholson Student Paper Competition, First Place

  Applied Probability Society Best Student Paper Award, Finalist

  Major Revision at a top journal. (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