Spectral bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Journal of Machine Learning Research Année : 2020

Spectral bandits

Tomáš Kocák
  • Fonction : Auteur
  • PersonId : 1029739
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863
Branislav Kveton
  • Fonction : Auteur
Michal Valko

Résumé

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this work, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each item we can recommend is a node of an undirected graph and its expected rating is similar to the one of its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret with respect to the optimal policy would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose three algorithms for solving our problem that scale linearly and sublinearly in this dimension. Our experiments on content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens of node evaluations.
Fichier principal
Vignette du fichier
kocak2020spectral.pdf (1005.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03084249 , version 1 (20-12-2020)

Identifiants

  • HAL Id : hal-03084249 , version 1

Citer

Tomáš Kocák, Rémi Munos, Branislav Kveton, Shipra Agrawal, Michal Valko. Spectral bandits. Journal of Machine Learning Research, 2020. ⟨hal-03084249⟩
66 Consultations
109 Téléchargements

Partager

Gmail Facebook X LinkedIn More