Diversity-Preserving K-Armed Bandits, Revisited

arXiv:2010.01874v2 Announce Type: replace-cross
Abstract: We consider the bandit-based framework for diversity-preserving recommendations introduced by Celis et al. (2019), who approached it in the case of a polytope mainly by a reduction to the setting of linear bandits. We design a UCB algorithm using the specific structure of the setting and show that it enjoys a bounded distribution-dependent regret in the natural cases when the optimal mixed actions put some probability mass on all actions (i.e., when diversity is desirable). …

abstract algorithm arxiv case cs.lg design diversity framework linear recommendations show stat.ml type