Fast evolution strategies

Xin YAO, Yong LIU

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

108 Citations (Scopus)

Abstract

Evolution strategies are a class of general optimisation algorithms which are applicable to functions that are multimodal, non differentiable, or even discontinuous. Although recombination operators have been introduced into evolution strategies, their primary search operator is still mutation. Classical evolution strategies rely on Gaussian mutations. A new mutation operator based on the Cauchy distribution is proposed in this paper. It is shown empirically that the new evolution strategy based on Cauchy mutation outperforms the classical evolution strategy on most of the 23 benchmark problems tested in this paper. These results, along with those obtained by fast evolutionary programming demonstrate that the superiority of Cauchy mutation is not dependent on any particular selection scheme. Cauchy mutation is applicable to a variety of evolutionary algorithms. © Springer-Verlag Berlin Heidelberg 1997.
Original languageEnglish
Title of host publicationEvolutionary Programming VI 6th International Conference, EP 97, Indianapolis, Indiana, USA, April 13-16, 1997, Proceedings
EditorsPeter J. ANGELINE, Robert G. REYNOLDS, John R. MCDONNELL, Russ EBERHART
PublisherSpringer Berlin Heidelberg
Pages149-161
Number of pages13
ISBN (Print)9783540627883
DOIs
Publication statusPublished - 1997
Externally publishedYes

Publication series

NameLecture Notes in Computer Science
Volume1213
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Keywords

  • Local Minimum
  • Evolution Strategy
  • Benchmark Problem
  • Search Operator
  • Unimodal Function

Fingerprint

Dive into the research topics of 'Fast evolution strategies'. Together they form a unique fingerprint.

Cite this