Black-box optimization of noisy functions with unknown smoothness - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Black-box optimization of noisy functions with unknown smoothness

Jean-Bastien Grill
  • Fonction : Auteur
  • PersonId : 972490
Michal Valko
Rémi Munos
  • Fonction : Auteur
  • PersonId : 836863

Résumé

We study the problem of black-box optimization of a function $f$ of any dimension, given function evaluations perturbed by noise. The function is assumed to be locally smooth around one of its global optima, but this smoothness is unknown. Our contribution is an adaptive optimization algorithm, POO or parallel optimistic optimization, that is able to deal with this setting. POO performs almost as well as the best known algorithms requiring the knowledge of the smoothness. Furthermore, POO works for a larger class of functions than what was previously considered, especially for functions that are difficult to optimize, in a very precise sense. We provide a finite-time analysis of POO's performance, which shows that its error after $n$ evaluations is at most a factor of $\sqrt{\ln n}$ away from the error of the best known optimization algorithms using the knowledge of the smoothness.
Fichier principal
Vignette du fichier
grill2015black-box.pdf (578.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01222915 , version 1 (31-10-2015)
hal-01222915 , version 2 (01-12-2015)
hal-01222915 , version 3 (29-01-2016)
hal-01222915 , version 4 (02-08-2018)

Identifiants

  • HAL Id : hal-01222915 , version 3

Citer

Jean-Bastien Grill, Michal Valko, Rémi Munos. Black-box optimization of noisy functions with unknown smoothness. Neural Information Processing Systems, Dec 2015, Montréal, Canada. ⟨hal-01222915v3⟩
1124 Consultations
1212 Téléchargements

Partager

Gmail Facebook X LinkedIn More