Population-based Algorithm Portfolios with automated constituent algorithms selection

Ke TANG, Fei PENG, Guoliang CHEN, Xin YAO

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

64 Citations (Scopus)

Abstract

Population-based Algorithm Portfolios (PAP) is an appealing framework for integrating different Evolutionary Algorithms (EAs) to solve challenging numerical optimization problems. Particularly, PAP has shown significant advantages to single EAs when a number of problems need to be solved simultaneously. Previous investigation on PAP reveals that choosing appropriate constituent algorithms is crucial to the success of PAP. However, no method has been developed for this purpose. In this paper, an extended version of PAP, namely PAP based on Estimated Performance Matrix (EPM-PAP) is proposed. EPM-PAP is equipped with a novel constituent algorithms selection module, which is based on the EPM of each candidate EAs. Empirical studies demonstrate that the EPM-based selection method can successfully identify appropriate constituent EAs, and thus EPM-PAP outperformed all single EAs considered in this work. © 2014 Elsevier Inc. All rights reserved.
Original languageEnglish
Pages (from-to)94-104
Number of pages11
JournalInformation Sciences
Volume279
Early online date3 Apr 2014
DOIs
Publication statusPublished - Sept 2014
Externally publishedYes

Keywords

  • Algorithm subset selection
  • Evolutionary optimization
  • Global optimization
  • Population-based Algorithm Portfolios

Fingerprint

Dive into the research topics of 'Population-based Algorithm Portfolios with automated constituent algorithms selection'. Together they form a unique fingerprint.

Cite this