Titre :

First-order regret bounds for combinatorial semi-bandits

Auteur(s) :

Neu, Gergely [Auteur]
Sequential Learning [SEQUEL]

Titre de la manifestation scientifique :

Proceedings of the 28th Annual Conference on Learning Theory (COLT)

Ville :

Paris

Pays :

France

Date de début de la manifestation scientifique :

2015-07-03

Titre de la revue :

JMLR Workshop and Conference Proceedings

Date de publication :

2015

Mot(s)-clé(s) en anglais :

online learning
online combinatorial optimization
semi-bandit feedback
follow the perturbed leader
improvements for small losses
first-order bounds

Discipline(s) HAL :

Informatique [cs]/Apprentissage [cs.LG]

Résumé en anglais : [en]

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated ...
Lire la suite >We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its action, but not other losses. For this problem, there are several learning algorithms that guarantee that the learner's expected regret grows as O(√ T) with the number of rounds T. In this paper, we propose an algorithm that improves this scaling to O(√ L * T), where L * T is the total loss of the best action. Our algorithm is among the first to achieve such guarantees in a partial-feedback scheme, and the first one to do so in a combinatorial setting.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL