A framework for memetic optimization using variable global and local surrogate models

Yoel Tenne, S. W. Armfield

Research output: Contribution to journalArticlepeer-review

53 Scopus citations

Abstract

We propose a framework of memetic optimization using variable global and local surrogate-models for optimization of expensive functions. The framework employs the trust-region approach but replaces the quadratic models with the more general RBF ones. It makes an extensive use of accuracy assessment to select the models used and to improve them if necessary. It also employs several efficient and stable numerical methods to improve its performance. Rigorous performance analysis shows the proposed framework significantly outperforms several existing surrogate-assisted evolutionary algorithms.

Original languageEnglish
Pages (from-to)781-793
Number of pages13
JournalSoft Computing
Volume13
Issue number8-9
DOIs
StatePublished - 2009
Externally publishedYes

Keywords

  • Accuracy assessment
  • Expensive black-box functions
  • Global-localsurrogate-models
  • Memetic algorithms
  • Trust-region
  • Variable models

Fingerprint

Dive into the research topics of 'A framework for memetic optimization using variable global and local surrogate models'. Together they form a unique fingerprint.

Cite this