Black-box optimization of noisy functions with unknown smoothness

Jean-Bastien Grill 1 Michal Valko 1 Rémi Munos 1, 2
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : 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.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-01222915
Contributor : Michal Valko <>
Submitted on : Thursday, August 2, 2018 - 6:37:06 PM
Last modification on : Friday, March 22, 2019 - 1:36:36 AM
Long-term archiving on : Saturday, November 3, 2018 - 3:54:30 PM

File

grill2015black-box.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01222915, version 4

Citation

Jean-Bastien Grill, Michal Valko, Rémi Munos. Black-box optimization of noisy functions with unknown smoothness. Neural Information Processing Systems, 2015, Montréal, Canada. ⟨hal-01222915v4⟩

Share

Metrics

Record views

281

Files downloads

137