Spectral bandits - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning Research Year : 2020

Spectral bandits

(1, 2) , (3, 2) , (4) , (5) , (3)
1
2
3
4
5
Tomáš Kocák
  • Function : Author
  • PersonId : 1029739
Rémi Munos
  • Function : Author
  • PersonId : 836863
Branislav Kveton
  • Function : Author
Michal Valko

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

  • HAL Id : hal-03084249 , version 1

Cite

Tomáš Kocák, Rémi Munos, Branislav Kveton, Shipra Agrawal, Michal Valko. Spectral bandits. Journal of Machine Learning Research, 2020. ⟨hal-03084249⟩
50 View
107 Download

Share

Gmail Facebook Twitter LinkedIn More