Skip to Main content Skip to Navigation
Conference papers

Noisy Optimization Complexity Under Locality Assumption

Jérémie Decock 1, 2 Olivier Teytaud 1, 2
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
2 LRI - Laboratoire de Recherche en Informatique
Abstract : In spite of various recent publications on the subject, there are still gaps between upper and lower bounds in evolutionary optimization for noisy objective function. In this paper we reduce the gap, and get tight bounds within logarithmic factors in the case of small noise and no long-distance influence on the objective function.
Keywords : Noisy optimization black box complexity model local sampling
Document type :
Conference papers
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download
https://hal.inria.fr/hal-00755663
Contributor : Jérémie Decock <>
Submitted on : Sunday, April 7, 2013 - 1:52:25 AM
Last modification on : Wednesday, September 16, 2020 - 5:06:42 PM
Long-term archiving on: : Monday, July 8, 2013 - 10:15:08 AM

Files

Vignette du document
foga006-decock.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00755663, version 1

Collections

CNRS | INRIA | INSMI | UMR8623 | LRI-AO | TDS-MACS

Citation

Jérémie Decock, Olivier Teytaud. Noisy Optimization Complexity Under Locality Assumption. FOGA - Foundations of Genetic Algorithms XII - 2013, Jan 2013, Adelaide, Australia. ⟨hal-00755663⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

823

Files downloads

441

 

Contact                    Legal Notice                    Personal Data