HELLINGER-UCB: A novel algorithm for stochastic multi-armed bandit problem and cold start problem in recommender system

arXiv:2404.10207v1 Announce Type: cross
Abstract: In this paper, we study the stochastic multi-armed bandit problem, where the reward is driven by an unknown random variable. We propose a new variant of the Upper Confidence Bound (UCB) algorithm called Hellinger-UCB, which leverages the squared Hellinger distance to build the upper confidence bound. We prove that the Hellinger-UCB reaches the theoretical lower bound. We also show that the Hellinger-UCB has a solid statistical interpretation. We show that Hellinger-UCB is effective in finite …

abstract algorithm arxiv cold start confidence cs.lg novel paper random stat.ml stochastic study type