Evolutionary Programming Using Mutations Based on the Lévy Probability Distribution

Chang-Yong LEE, Xin YAO

Research output: Journal PublicationsJournal Article (refereed)peer-review

447 Citations (Scopus)

Abstract

This paper studies evolutionary programming with mutations based on the Lévy probability distribution. The Lévy probability distribution has an infinite second moment and is, therefore, more likely to generate an offspring that is farther away from its parent than the commonly employed Gaussian mutation. Such likelihood depends on a parameter α in the Lévy distribution. We propose an evolutionary programming algorithm using adaptive as well as nonadaptive Lévy mutations. The proposed algorithm was applied to multivariate functional optimization. Empirical evidence shows that, in the case of functions having many local optima, the performance of the proposed algorithm was better than that of classical evolutionary programming using Gaussian mutation.
Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalIEEE Transactions on Evolutionary Computation
Volume8
Issue number1
DOIs
Publication statusPublished - Feb 2004
Externally publishedYes

Bibliographical note

This work was supported in part by Kongju National University, Korea, and the Royal Society, U.K., 2000–2001.

Keywords

  • Evolutionary optimization
  • Evolutionary programming
  • Lévy probability distribution
  • Levy mutation
  • Mean-square displacement

Fingerprint

Dive into the research topics of 'Evolutionary Programming Using Mutations Based on the Lévy Probability Distribution'. Together they form a unique fingerprint.

Cite this