Hybrid Stochastic-Adversarial On-line Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Hybrid Stochastic-Adversarial On-line Learning

Lazaric Alessandro
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

Most of the research in online learning focused either on the problem of adversarial classification (i.e., both inputs and labels are arbitrarily chosen by an adversary) or on the traditional supervised learning problem in which samples are indepen- dently generated from a fixed probability distribution. Nonetheless, in a number of domains the relationship between inputs and labels may be adversarial, whereas input instances are generated according to a constant distribution. This scenario can be formalized as an hybrid classification problem in which inputs are stochastic, while labels are adversarial. In this paper, we introduce this hybrid stochastic-adversarial classification problem, we propose an online learning algorithm for its so- lution, and we analyze its performance. In particular, we show that, given a hypothesis space H with finite VC dimension, it is possible to incrementally build a suitable finite set of hypotheses that can be used as input for an exponentially weighted forecaster achieving a cumulative regret of order O( n VC(H) log n) with overwhelming probability. Finally, we discuss extensions to multi-label classification, learning from experts and bandit set- tings with stochastic side information, and application to games.
Fichier principal
Vignette du fichier
estochad.pdf (167.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00392524 , version 1 (08-06-2009)

Identifiants

  • HAL Id : inria-00392524 , version 1

Citer

Lazaric Alessandro, Rémi Munos. Hybrid Stochastic-Adversarial On-line Learning. COLT 2009 - 22nd Conference on Learning Theory, Jun 2009, Montreal, Canada. ⟨inria-00392524⟩
346 Consultations
229 Téléchargements

Partager

Gmail Facebook X LinkedIn More