Talk Title

Bridging Online and Offline Learning Towards Improved Data-Driven Operations Management

Abstract

Modern organizations’ operations require increasing use of machine learning tools. While supervised machine learning traditionally excels at making predictions based on i.i.d. offline data, many modern operational tasks require making sequential decisions based on data collected online. Bridging the gap between offline supervised learning and online interactive learning may help significantly improve data-driven operations.

In this talk, we show how difficult online decision-making problems can be reduced to well-understood offline regression problems. Focusing on contextual bandits, a core class of online decision-making problems that find broad applications in electronic commerce and personalized medicine, we present the first approach that automatically translates advances in offline regression into contextual bandits, optimally and efficiently. We demonstrate the impact of our approach using real-world datasets from personalized product recommendation and dynamic pricing.

Bio

Yunzong Xu is a fifth-year PhD student in the Institute for Data, Systems, and Society at MIT, advised by Prof. David Simchi-Levi. His research lies at the intersection of operations research and data analytics.

His current research interests include data-driven decision making, online and reinforcement learning, econometrics and causal inference, motivated by modern challenges in e-commerce, supply chains, and healthcare. Over the course of his PhD, his research has been recognized by multiple paper awards, including finalists in the INFORMS George Nicholson and Applied Probability Society best student paper competitions. His industrial experience includes an internship at Microsoft Research on reinforcement learning, as well as an ongoing research collaboration with IBM and Boston Scientific on healthcare inventory management. Prior to joining MIT, he received his dual bachelor’s degrees in information systems and mathematics from Tsinghua University in 2018.

Location

1174 Etcheverry Hall or Join via Zoom