Optimisic Information Directed Sampling

arXiv:2402.15411v1 Announce Type: new
Abstract: We study the problem of online learning in contextual bandit problems where the loss function is assumed to belong to a known parametric function class. We propose a new analytic framework for this setting that bridges the Bayesian theory of information-directed sampling due to Russo and Van Roy (2018) and the worst-case theory of Foster, Kakade, Qian, and Rakhlin (2021) based on the decision-estimation coefficient. Drawing from both lines of work, we propose a algorithmic …

abstract arxiv bayesian class cs.lg framework function information loss online learning parametric sampling study theory type van