Optimistic optimization of deterministic functions without the knowledge of its smoothness

Rémi Munos 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00830143
Contributor : Rémi Munos <>
Submitted on : Tuesday, June 4, 2013 - 2:56:23 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Thursday, September 5, 2013 - 4:22:38 AM

File

opti2_nips2011.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00830143, version 1

Collections

Citation

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

Share

Metrics

Record views

685

Files downloads

293