A Median Success Rule for Non-Elitist Evolution Strategies: Study of Feasibility

Ouassim Ait Elhara 1 Anne Auger 1 Nikolaus Hansen 1
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Success rule based step-size adaptation, namely the one-fifth success rule, has shown to be effective for single parent evolution strategies (ES), e.g. the (1+1)-ES. The success rule remains feasible in non-elitist single parent strategies, where the target success rate must be roughly inversely proportional to the population size. This success rule is, however, not easily applicable to multi-parent strategies. In this paper, we introduce the idea of median success adaptation for the step-size, applicable to non-elitist multi-recombinant evolution strategies. In median success adaptation, the median fitness of the population is compared to a fitness from the previous iteration. The comparison fitness is chosen to achieve a target success rate of 1/2, thereby a deviation from the target can be measured robustly in a few iteration steps. As a prerequisite for feasibility of the median success rule, we studied the way the comparison index depends on the search space dimension, the population size, the parent number, the recombination weights and the objective function. The findings are encouraging: the choice of the comparison index appears to be relatively uncritical and experiments on a variety of functions, also in combination with CMA, reveal reasonable behavior.
Document type :
Conference papers
Christian, Blum et al. Genetic and Evolutionary Computation Conference, Jul 2013, Amsterdam, Netherlands. ACM Press, pp.415-422, 2013
Liste complète des métadonnées

https://hal.inria.fr/hal-00801414
Contributor : Ouassim Ait Elhara <>
Submitted on : Tuesday, October 21, 2014 - 2:15:44 PM
Last modification on : Thursday, February 9, 2017 - 3:58:06 PM
Document(s) archivé(s) le : Friday, April 14, 2017 - 1:02:19 PM

Files

Identifiers

  • HAL Id : hal-00801414, version 3

Citation

Ouassim Ait Elhara, Anne Auger, Nikolaus Hansen. A Median Success Rule for Non-Elitist Evolution Strategies: Study of Feasibility. Christian, Blum et al. Genetic and Evolutionary Computation Conference, Jul 2013, Amsterdam, Netherlands. ACM Press, pp.415-422, 2013. <hal-00801414v3>

Share

Metrics

Record views

363

Document downloads

159