Yunbei Xu

Ph.D. student

Decision, Risk, and Operations

Columbia University, Graduate School of Business

Email: yunbei.xu [at]


B.Sc. in Mathematics, Peking University, 2018

Research interests

• Machine learning: statistical learning theory, reinforcement learning, causal inference

• Operations research: decision-making, applied probability, optimization

Preprints/Under review

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

with Assaf Zeevi. 

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

with Assaf Zeevi.

Journal articles

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

with Yanli Liu and Wotao Yin. Journal of Scientific Computing, 2021Software codes

Conference proceedings

•  Towards Problem-dependent Optimal Learning Rates

with Assaf Zeevi. Conference on Neural Information Processing Systems (NeurIPS) 2020 (Spotlight; top 2.9% of submissions).

Teaching experience

Teaching assistant, Statistical Physics, Markets and Algorithms, Fall 2019, Columbia Business School