Yunbei Xu (许云贝)

Research

• Pointwise Generalization in Deep Neural Networks

  with Shaojie Li.

  Working paper.

• Finite-Time Minimax Bounds and an Optimal Lyapunov Policy in Queueing Control

  with Yujie Liu and Vincent Tan.

  Major Revision at Operations Research.

• Autoregressive Learning under Joint KL Analysis

  with Yuzhe Yuan and Ruohan Zhan.

  Submitted to COLT 2026.

  Spotlight (top 4.3%)in NeurIPS 2025 ML×OR Workshop.

• Statistical Properties of Robust Learning under Distribution Shifts

  with Zhiyi Li, Xiaojia Mao, and Ruohan Zhan.

  Working paper.

• Breaking the Trap of Random Initialization: On the Blessing of Pre-training in Weak-to-Strong Generalization

  with Wei Yao, Wang Zhaoyang, Gengze Xu, Chen Qian, Dongrui Liu, Ziqiao Wang, and Yong Liu.

  Submitted to ICML 2026.

• On the Power of Adaptivity for ε-Best Arm Identification in Linear Bandits

  with Arnab Maiti and Kevin Jamieson.

  Submitted to COLT 2026.

• In-context Learning for Data-driven Censored Inventory Control

  with Sohom Mukherjee, Anh-Duy Pham,and Richard Pibernik.

  Submitted to EC 2026.

• Thompson Sampling for Repeated Newsvendor

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

  Working paper.

• Triply Robust Causal Estimation For Continuous Treatments

  with Hongseok Namkoong and Shunri Zheng.

  Working paper.

• 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 (top 2.5%)

  Journal version in preparation.

• Statistical Properties of Robust Satisficing

  with Zhiyi Li and Ruohan Zhan.

  International Conference on Machine Learning (ICML) 2024.

  INFORMS Undergraduate Operations Research Prize, Finalist

• 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

• 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 4.1%)

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

  with Assaf Zeevi.

  Under Revision at Journal of Machine Learning Research.

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

  with Yanli Liu and Wotao Yin.

  Journal of Scientific Computing, 2021. Code