2017/07/27 by Mastane Achab, Stephan Clémençon, Stéphan Clémençon +8
Computer Science · Decision Sciences · Mathematics · #Advanced Bandit Algorithms Research #Optimization and Search Problems #Risk and Portfolio Optimization #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1707.08820
arxiv created 2017/07/27 · arxiv updated 2017/07/28
This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose an alternative approach, showing that, remarkably, Extreme Bandits can be reduced to a classical version of the bandit problem to a certain extent. Beyond the formal analysis, these two approaches are compared through numerical experiments.