Title :

First-order regret bounds for combinatorial semi-bandits

Author(s) :

Neu, Gergely [Auteur]
Sequential Learning [SEQUEL]

Conference title :

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

City :

Paris

Country :

France

Start date of the conference :

2015-07-03

Journal title :

JMLR Workshop and Conference Proceedings

Publication date :

2015

English keyword(s) :

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

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

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

Source :

Harvested from HAL