Time: Friday, May 22, 2026, 1:30-3:00 p.m.

Venue: Room 524, Siyuan Building, Guoshun Campus

Topic: Contextual Linear Optimization under Full and Partial Feedback

Speaker: Associate Professor Xiaojie Mao, Department of Management Science and Engineering, School of Economics and Management, Tsinghua University

Host: Professor Tianjun Feng

Abstract: This talk examines Contextual Linear Optimization (CLO) under two feedback regimes, focusing on both the traditional two-stage Estimate-Then-Optimize (ETO) approach and the newly integrated Induced Empirical Risk Minimization (IERM) framework. In the full-feedback setting, we theoretically demonstrate that under correct model specification, ETO can surprisingly achieve faster regret convergence rates than IERM by leveraging problem-specific geometric properties. In partial-feedback settings, including bandit and semi-bandit regimes, we propose a unified offline IERM framework and establish novel fast-rate guarantees. Numerical experiments on shortest path problems further validate the theoretical findings across different feedback regimes.

Bio: Xiaojie Mao is an Associate Professor in the Department of Management Science and Engineering at the School of Economics and Management, Tsinghua University. He received his bachelor's degree in Mathematical Economics and Mathematical Finance from Wuhan University in 2016 and earned his Ph.D. in Statistics and Data Science from Cornell University in 2021. His research focuses on causal inference, data-driven decision-making theories and methods, and statistical machine learning. His work has been published in leading journals and conferences in operations management, statistics, and machine learning, including Management Science, Operations Research, Information Systems Research, Journal of Machine Learning Research, Journal of the Royal Statistical Society Series B, NeurIPS, ICML, and COLT.