Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Diversity-Preserving K-Armed Bandits, Revisited

Abstract : We consider the bandit-based framework for diversity-preserving recommendations introduced by Celis et al. (2019), who approached it 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). Simulations illustrate this fact. We also provide regret lower bounds and briefly discuss distribution-free regret bounds.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Gilles Stoltz Connect in order to contact the contributor
Submitted on : Monday, October 5, 2020 - 11:16:40 AM
Last modification on : Monday, July 4, 2022 - 9:19:23 AM


Files produced by the author(s)


  • HAL Id : hal-02957485, version 1
  • ARXIV : 2010.01874


Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz. Diversity-Preserving K-Armed Bandits, Revisited. 2020. ⟨hal-02957485⟩



Record views


Files downloads