Optimistic optimization of deterministic functions without the knowledge of its smoothness - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Optimistic optimization of deterministic functions without the knowledge of its smoothness

Rémi Munos
  • Function : Author
  • PersonId : 836863

Abstract

We consider a global optimization problem of a deterministic function f in a semi-metric space, given a finite budget of n evaluations. The function f is assumed to be locally smooth (around one of its global maxima) with respect to a semi-metric. We describe two algorithms based on optimistic exploration that use a hierarchical partitioning of the space at all scales. A first contribution is an algorithm, DOO, that requires the knowledge of . We report a finite-sample performance bound in terms of a measure of the quantity of near-optimal states. We then define a second algorithm, SOO, which does not require the knowledge of the semi-metric under which f is smooth, and whose performance is almost as good as DOO optimally-fitted.
Fichier principal
Vignette du fichier
opti2_nips2011.pdf (135.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00830143 , version 1 (04-06-2013)

Identifiers

  • HAL Id : hal-00830143 , version 1

Cite

Rémi Munos. Optimistic optimization of deterministic functions without the knowledge of its smoothness. Advances in Neural Information Processing Systems, 2011, Spain. ⟨hal-00830143⟩
561 View
338 Download

Share

Gmail Facebook Twitter LinkedIn More