ISyE Seminar "Adaptivity and Confounding in Multi-armed Bandit Experiments"
Please join us for our next seminar in person! This seminar will feature Daniel Russo from Columbia University who will discuss adaptivity and confounding in multi-armed bandit experiments.
Note: All seminars this semester will be research-focused.
Wednesday, April 20, 2022
3 p.m. - Reception
3:30 p.m. - Graduate seminar
About the seminar
This talk explores a new model of bandit experiments where a potentially nonstationary sequence of contexts influences arms’ performance. Context-unaware algorithms risk confounding while those that perform correct inference face information delays. Professor Russo and his team's main insight is that an algorithm they call deconfounted Thompson sampling strikes a delicate balance between adaptivity and robustness. Its adaptivity leads to optimal efficiency properties in easy stationary instances, but it displays surprising resilience in hard nonstationary ones which cause other adaptive algorithms to fail.
For context, read their paper, "Adaptivity and Confounding in Multi-Armed Bandit Experiments."
About the speaker
Daniel Russo is an associate professor in the Decision, Risk, and Operations division of the Columbia Business School. His research lies at the intersection of statistical machine learning and online decision making, mostly falling under the broad umbrella of reinforcement learning. Outside academia, Russo works with Spotify to apply reinforcement learning style models to audio recommendations.