Instance-Sensitive Algorithms for Pure Exploration in Multinomial Logit Bandit

Motivated by real-world applications such as fast fashion retailing and online advertising, the Multinomial Logit Bandit (MNL-bandit) is a popular model in online learning and operations research, and has attracted much attention in the past decade. In this paper, we give efficient algorithms for pure exploration in MNL-bandit. Our algorithms achieve instancesensitive pull complexities. We also complement the upper bounds by an almost matching lower bound. * N. Karpov and Q. Zhang are supported in part by CCF-1844234 and CCF-2006591.