Average Convergence Rate of Evolutionary Algorithms

Jun He, Guangming Lin

Research output: Contribution to journalArticlepeer-review

46 Citations (SciVal)
249 Downloads (Pure)

Abstract

In evolutionary optimization, it is important to understand how fast evolutionary algorithms converge to the optimum per generation, or their convergence rates. This paper proposes a new measure of the convergence rate, called the average convergence rate. It is a normalized geometric mean of the reduction ratio of the fitness difference per generation. The calculation of the average convergence rate is very simple and it is applicable for most evolutionary algorithms on both continuous and discrete optimization. A theoretical study of the average convergence rate is conducted for discrete optimization. Lower bounds on the
average convergence rate are derived. The limit of the average convergence rate is analyzed and then the asymptotic average convergence rate is proposed.
Original languageEnglish
Pages (from-to)316-321
Number of pages6
JournalIEEE Transactions on Evolutionary Computation
Volume20
Issue number2
DOIs
Publication statusPublished - 11 Jun 2015

Keywords

  • matrix analysis
  • evolutionary algorithms
  • evolutionary optimization
  • convergence rate
  • Markov chain

Fingerprint

Dive into the research topics of 'Average Convergence Rate of Evolutionary Algorithms'. Together they form a unique fingerprint.

Cite this