11/15/18 | 4:15pm | E51-335
Reception to follow.

Mohsen Bayati

Associate Professor
Stanford University 

Abstract: A central problem in personalized decision-making is to learn decision outcomes as functions of individual-specific covariates (contexts). Current literature on this topic focuses on algorithms that balance an exploration-exploitation tradeoff, to ensure sufficient rate of learning while optimizing for some objective. However, exploration may be undesirable for highly sensitive individuals (e.g., patients in clinical treatment planning). In this talk, we first introduce an algorithm that leverages free-exploration from the covariates and achieves rate optimal objective. Moreover, we show empirically that our algorithm significantly reduces exploration, compared to existing benchmarks. Next, we focus on settings when past data on decision outcomes is available or when the number of decisions is large. Motivated by literature on low-rank matrix estimation, we design algorithms that avoid unnecessary exploration by targeting the learning towards shared similarities among decisions or patients.

Bio: Mohsen received is associate professor of Operations, Information, and Technology at Stanford University Graduate School of Business. Prior to joining Stanford faculty in 2011, he was postdoc in Stanford University and Microsoft Research. Mohsen’s research is on healthcare management, statistical inference via graphical models, and personalized decision-making. His research as received the INFORMS Healthcare Applications Society best paper (Pierskalla) award in 2014 and in 2016, INFORMS Applied Probability Society best paper award in 2015, and National Science Foundation CAREER award.