Department of Industrial Engineering & Decision Analytics [Seminar] - Fast Rates for Contextual Linear Optimization

2:30pm - 4:00pm
Room 5583 (lift 29-30)

Incorporating side observations in decision making can reduce uncertainty and boost performance, but it also requires that we tackle a potentially complex predictive relationship. Although one may use off-the-shelf machine learning methods to separately learn a predictive model and plug it in, a variety of recent methods instead integrate estimation and optimization by fitting the model to directly optimize downstream decision performance. Surprisingly, in the case of contextual linear optimization, we show that the naïve plug-in approach actually achieves regret convergence rates that are significantly faster than methods that directly optimize downstream decision performance. We show this by leveraging the fact that specific problem instances do not have arbitrarily bad near-dual-degeneracy. Although there are other pros and cons to consider as we discuss and illustrate numerically, our results highlight a nuanced landscape for the enterprise to integrate estimation and optimization. Our results are overall positive for practice: predictive models are easy and fast to train using existing tools; simple to interpret; and, as we show, lead to decisions that perform very well.

Event Format
Speakers / Performers:
Prof. Xiaojie MAO
Management Science and Engineering, Tsinghua University

Xiaojie Mao is an assistant professor of Management Science and Engineering at Tsinghua University. He received his BS in Mathematical Economics from Wuhan University (2016) and Ph.D. in Statistics and Data Science from Cornell University (2021). His research interest is in causal inference and data-driven decision-making, at the intersection of statistics, operations research, and machine learning. His research has appeared in top journals and conferences, such as Operations ResearchManagement ScienceConference on Neural Information Processing Systems (NeurIPS)International Conference on Machine Learning (ICML)International Conference on Artificial Intelligence and Statistics (AISTATS). 

Recommended For
Faculty and staff
PG students
Department of Industrial Engineering & Decision Analytics
Department of Information Systems, Business Statistics & Operations Management
Post an event
Campus organizations are invited to add their events to the calendar.