Stochastic Simultaneous Optimistic Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Stochastic Simultaneous Optimistic Optimization

Michal Valko
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

We study the problem of global maximization of a function f given a finite number of evaluations perturbed by noise. We consider a very weak assumption on the function, namely that it is locally smooth (in some precise sense) with respect to some semi-metric, around one of its global maxima. Compared to previous works on bandits in general spaces (Kleinberg et al., 2008; Bubeck et al., 2011a) our algorithm does not require the knowledge of this semi-metric. Our algorithm, StoSOO, follows an optimistic strategy to iteratively construct upper confidence bounds over the hierarchical partitions of the function domain to decide which point to sample next. A finite-time analysis of StoSOO shows that it performs almost as well as the best specifically-tuned algorithms even though the local smoothness of the function is not known.
Fichier principal
Vignette du fichier
paper.pdf (569.53 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00789606 , version 1 (15-04-2013)
hal-00789606 , version 2 (30-05-2013)

Identifiants

  • HAL Id : hal-00789606 , version 1

Citer

Michal Valko, Alexandra Carpentier, Rémi Munos. Stochastic Simultaneous Optimistic Optimization. 30th International Conference on Machine Learning, Jun 2013, Atlanta, United States. ⟨hal-00789606v1⟩
828 Consultations
465 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More