Analyzing the Impact of Mirrored Sampling and Sequential Selection in Elitist Evolution Strategies

Anne Auger 1 Dimo Brockhoff 2 Nikolaus Hansen 1, 3, 4
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
2 X - École polytechnique
3 LRI - Laboratoire de Recherche en Informatique
4 MSR - INRIA - Microsoft Research - Inria Joint Centre
Abstract : This paper presents a refined single parent evolution strategy that is derandomized with mirrored sampling and/or uses sequential selection. The paper analyzes some of the elitist variants of this algorithm. We prove, on spherical functions with finite dimension, linear convergence of different strategies with scale-invariant step-size and provide expressions for the convergence rates as the expectation of some known random variables. In addition, we derive explicit asymptotic formulae for the convergence rate when the dimension of the search space goes to infinity. Convergence rates on the sphere reveal lower bounds for the convergence rate of the respective step-size adaptive strategies. We prove the surprising result that the (1+2)-ES with mirrored sampling converges at the same rate as the (1+1)-ES without and show that the tight lower bound for the (1+λ)-ES with mirrored sampling and sequential selection improves by 16% over the (1+1)-ES reaching an asymptotic value of about -0.235.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download
https://hal.inria.fr/inria-00587507
Contributor : Dimo Brockhoff <>
Submitted on : Wednesday, April 20, 2011 - 3:20:57 PM
Last modification on : Monday, December 9, 2019 - 5:24:06 PM
Long-term archiving on: Thursday, July 21, 2011 - 3:08:23 AM

File

foga22v-augerAuthorVersion.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | INRIA | UMR8623 | LRI-AO | X | PARISTECH

Citation

Anne Auger, Dimo Brockhoff, Nikolaus Hansen. Analyzing the Impact of Mirrored Sampling and Sequential Selection in Elitist Evolution Strategies. Foundations of Genetic Algorithms (FOGA 2011), Jan 2011, Schwarzenberg, Austria. pp.127-138, ⟨10.1145/1967654.1967666⟩. ⟨inria-00587507⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

797

Files downloads

387

 

 

Contact

archive-ouverte@inria.fr