Local meta-models for optimization using evolution strategies

  • Authors:
  • Stefan Kern;Nikolaus Hansen;Petros Koumoutsakos

  • Affiliations:
  • Computational Science and Engineering Laboratory, Institute of Computational Science, ETH Zurich, Switzerland;Computational Science and Engineering Laboratory, Institute of Computational Science, ETH Zurich, Switzerland;Computational Science and Engineering Laboratory, Institute of Computational Science, ETH Zurich, Switzerland

  • Venue:
  • PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We employ local meta-models to enhance the efficiency of evolution strategies in the optimization of computationally expensive problems. The method involves the combination of second order local regression meta-models with the Covariance Matrix Adaptation Evolution Strategy. Experiments on benchmark problems demonstrate that the proposed meta-models have the potential to reliably account for the ranking of the offspring population resulting in significant computational savings. The results show that the use of local meta-models significantly increases the efficiency of already competitive evolution strategies.