Online Learning in Adversarial Lipschitz Environments - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Online Learning in Adversarial Lipschitz Environments

Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

We consider the problem of online learning in an adversarial environment when the reward functions chosen by the adversary are assumed to be Lipschitz. This setting extends previous works on linear and convex online learning. We provide a class of algorithms with cumulative regret upper bounded by O(sqrt{dT ln(λ)}) where d is the dimension of the search space, T the time horizon, and λ the Lipschitz constant. Efficient numerical implementations using particle methods are discussed. Applications include online supervised learning problems for both full and partial (bandit) information settings, for a large class of non-linear regressors/classifiers, such as neural networks.
Fichier principal
Vignette du fichier
ALF_ecml10.pdf (286.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00510674 , version 1 (20-08-2010)

Identifiants

  • HAL Id : inria-00510674 , version 1

Citer

Odalric Maillard, Rémi Munos. Online Learning in Adversarial Lipschitz Environments. European Conference on Machine Learing, 2010, Barcelone, Spain. ⟨inria-00510674⟩
180 Consultations
827 Téléchargements

Partager

Gmail Facebook X LinkedIn More