Online allocation and homogeneous partitioning for piecewise constant mean-approximation

Abstract : In the setting of active learning for the multi-armed bandit, where the goal of a learner is to estimate with equal precision the mean of a finite number of arms, recent results show that it is possible to derive strategies based on finite-time confidence bounds that are competitive with the best possible strategy. We here consider an extension of this problem to the case when the arms are the cells of a finite partition P of a continuous sampling space X \subset \Real^d. Our goal is now to build a piecewise constant approximation of a noisy function (where each piece is one region of P and P is fixed beforehand) in order to maintain the local quadratic error of approximation on each cell equally low. Although this extension is not trivial, we show that a simple algorithm based on upper confidence bounds can be proved to be adaptive to the function itself in a near-optimal way, when |P| is chosen to be of minimax-optimal order on the class of \alpha-Hölder functions.
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00742893
Contributeur : Odalric-Ambrym Maillard <>
Soumis le : jeudi 1 novembre 2012 - 07:00:35
Dernière modification le : lundi 13 octobre 2014 - 15:43:25
Document(s) archivé(s) le : samedi 17 décembre 2016 - 01:58:32

Fichier

nips965supplementary.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00742893, version 1

Collections

Citation

Odalric-Ambrym Maillard, Alexandra Carpentier. Online allocation and homogeneous partitioning for piecewise constant mean-approximation. 22. 2012. 〈hal-00742893〉

Partager

Métriques

Consultations de la notice

197

Téléchargements de fichiers

46