Categorized Bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Categorized Bandits

Résumé

We introduce a new stochastic multi-armed bandit setting where arms are grouped inside ``ordered'' categories. The motivating example comes from e-commerce, where a customer typically has a greater appetence for items of a specific well-identified but unknown category than any other one. We introduce three concepts of ordering between categories, inspired by stochastic dominance between random variables, which are gradually weaker so that more and more bandit scenarios satisfy at least one of them. We first prove instance-dependent lower bounds on the cumulative regret for each of these models, indicating how the complexity of the bandit problems increases with the generality of the ordering concept considered. We also provide algorithms that fully leverage the structure of the model with their associated theoretical guarantees. Finally, we have conducted an analysis on real data to highlight that those ordered categories actually exist in practice.

Dates et versions

hal-03089789 , version 1 (28-12-2020)

Identifiants

Citer

Matthieu Jedor, Jonathan Louëdec, Vianney Perchet. Categorized Bandits. Advances in Neural Information Processing Systems, 2019, Long Beach, France. ⟨hal-03089789⟩
29 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More