Yunbei Xu

Email: yunbei [at]

I am broadly interested in machine learning, operations research, and mathematical physics.


Postdoc, MIT, 2023-2024

   Statistics and Data Science Center, Institute for Data, Systems, and Society

   Advisor: Sasha Rakhlin

Ph.D., Columbia University, 2018-2023

   Decision, Risk, and Operations, Graduate School of Business

   Advisor: Assaf Zeevi

B.Sc., Peking University, 2014-2018

   Department of Mathematics, School of Mathematical Sciences

Starting Fall 2024, I will be an Assistant Professor at NUS, affiliated with ISEM and IORA. 


•  Bayesian Design Principles for Frequentist Sequential Learning

   with Assaf Zeevi. 

    - International Conference on Machine Learning (ICML) 2023.

    - Outstanding Paper Award; Oral

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

   with Assaf Zeevi. 

    - Minor Revision in Mathematics of Operations Research

    - 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.

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

   with Yanli Liu and Wotao Yin.

    - Journal of Scientific Computing, 2021. Code

•  Offline Learning from Partial Feedback with Continuous Actions

   with Khashayar Khosravi and Hongseok Namkoong. 


Instructor: Real Analysis Math Camp (Fall 2021)

Teaching Assistant: Managerial Statistics (Fall 2022 & Fall 2021, instructed by Assaf Zeevi)

Teaching Assistant: Statistical Physics, Markets and Algorithms (Fall 2019, instructed by Yash Kanoria)