Hybrid Stochastic-Adversarial On-line Learning

Lazaric Alessandro 1 Rémi Munos 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : 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.
Type de document :
Article dans une revue
COLT, COLT, 2009
Liste complète des métadonnées

Littérature citée [2 références]  Voir  Masquer  Télécharger

Contributeur : Rémi Munos <>
Soumis le : lundi 8 juin 2009 - 12:00:26
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : vendredi 11 juin 2010 - 00:27:45


Fichiers produits par l'(les) auteur(s)


  • HAL Id : inria-00392524, version 1



Lazaric Alessandro, Rémi Munos. Hybrid Stochastic-Adversarial On-line Learning. COLT, COLT, 2009. 〈inria-00392524〉



Consultations de la notice


Téléchargements de fichiers