Black-box optimization of noisy functions ...
Document type :
Communication dans un congrès avec actes
Title :
Black-box optimization of noisy functions with unknown smoothness
Author(s) :
Grill, Jean-Bastien [Auteur]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
Munos, Rémi [Auteur]
DeepMind [London]
Sequential Learning [SEQUEL]
Sequential Learning [SEQUEL]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
Munos, Rémi [Auteur]
DeepMind [London]
Sequential Learning [SEQUEL]
Conference title :
Neural Information Processing Systems
City :
Montréal
Country :
Canada
Start date of the conference :
2015
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Recherche d'information [cs.IR]
Informatique [cs]/Recherche d'information [cs.IR]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-01222915v4/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01222915v4/document
- Open access
- Access the document
- document
- Open access
- Access the document
- grill2015black-box.pdf
- Open access
- Access the document