Title: Multi-armed Bandits with Covariates: Theory and Applications
Speaker: Prof. Tze Leung Lai, Department of Statistics, Stanford University
Abstract: In the past five years, multi-armed bandits with covariates, also called "contextual bandits" in machine learning, have become an active area of research in data science, stochastic optimization, and statistical modeling because of their applications to the development of personalized strategies in translational medicine and in recommender systems for web-based marketing and electronic business. After a brief review of the relatively complete classical (context-free) bandit theory, we describe a corresponding theory, covering both parametric and nonparametric approaches, for contextual bandits and illustrate their applications to personalized strategies.
For More Information Contact
Yajun Mei and Jeff Wu
Georgia Institute of Technology North Avenue, Atlanta, GA 30332 Phone: 404-894-2000