Diversity-Preserving K-Armed Bandits, Revisited - IRT Saint Exupéry - Institut de Recherche Technologique
Pré-Publication, Document De Travail Année : 2024

Diversity-Preserving K-Armed Bandits, Revisited

Résumé

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). The regret lower bounds provided show that otherwise, at least when the model is mean-unbounded, a regret is suffered. We also discuss an example beyond the special case of polytopes.
Fichier principal
Vignette du fichier
GHLS24--Diversity-preserving.pdf (399.38 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02957485 , version 1 (05-10-2020)
hal-02957485 , version 2 (05-04-2024)
hal-02957485 , version 3 (17-07-2024)

Licence

Identifiants

Citer

Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz. Diversity-Preserving K-Armed Bandits, Revisited. 2024. ⟨hal-02957485v2⟩
551 Consultations
198 Téléchargements

Altmetric

Partager

More