Contextual Linear Optimization under Full and Partial Feedback
Prof. Xiaojie Mao
Associate Professor
Department of Management Science and Engineering
Tsinghua University
This talk is about Contextual Linear Optimization (CLO) across two feedback regimes, where we study the traditional two-stage Estimate-Then-Optimize (ETO) approach and the new integrated Induced Empirical Risk Minimization (IERM) framework. In the full-feedback setting, we theoretically demonstrate that under model correct specification, ETO can surprisingly achieve faster regret convergence rates than IERM by leveraging problem-specific geometric properties.
In partial-feedback settings (bandit and semi-bandit), we propose a unified offline IERM framework and establish novel fast-rate guarantees. Numerical experiments on shortest path problems validate our theoretical findings across different regimes.
Xiaojie Mao is an associate professor in Management Science and Engineering at Tsinghua University. He did his undergraduate in Mathematical Economics at Wuhan University and Ph.D. in Statistics and Data Science at Cornell University. His research interest is in causal inference, data-driven decision-making, and statistical machine learning. His research has appeared in top journals and conferences across multiple disciplines, such as Management Science, Operations Research, Information Systems Research, Journal of Machine Learning Research, Journal of the Royal Statistical Society Series B, NeurIPS, ICML, AISTATS, COLT, etc.
