Markov Chain Analysis of Evolution Strategies on a Linear Constraint Optimization Problem

Alexandre Chotard 1, 2, * Anne Auger 1 Nikolaus Hansen 1
* Corresponding author
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 : This paper analyses a $(1,\lambda)$-Evolution Strategy, a randomised comparison-based adaptive search algorithm, on a simple constraint optimisation problem. The algorithm uses resampling to handle the constraint and optimizes a linear function with a linear constraint. Two cases are investigated: first the case where the step-size is constant, and second the case where the step-size is adapted using path length control. We exhibit for each case a Markov chain whose stability analysis would allow us to deduce the divergence of the algorithm depending on its internal parameters. We show divergence at a constant rate when the step-size is constant. We sketch that with step-size adaptation geometric divergence takes place. Our results complement previous studies where stability was assumed.
Document type :
Conference papers
Amir Hussain; Zhigang Zeng; Nian Zhang. IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China. 2014
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-00977379
Contributor : Alexandre Chotard <>
Submitted on : Friday, December 5, 2014 - 2:44:17 PM
Last modification on : Thursday, February 9, 2017 - 3:58:39 PM
Document(s) archivé(s) le : Monday, March 9, 2015 - 7:55:29 AM

Files

chotard2014linearconstraint_ca...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00977379, version 2
  • ARXIV : 1404.3023

Citation

Alexandre Chotard, Anne Auger, Nikolaus Hansen. Markov Chain Analysis of Evolution Strategies on a Linear Constraint Optimization Problem. Amir Hussain; Zhigang Zeng; Nian Zhang. IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China. 2014. 〈hal-00977379v2〉

Share

Metrics

Record views

364

Document downloads

83