Skip to Main content Skip to Navigation
Conference papers

Algorithms (X,sigma,eta) : quasi-random mutations for Evolution Strategies

Olivier Teytaud 1 Mohamed Jebalia 1 Anne Auger 1
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : Randomization is an efficient tool for global optimization. We here define a method which keeps : - the order 0 of evolutionary algorithms (no gradient) ; - the stochastic aspect of evolutionary algorithms ; - the efficiency of so-called "low-dispersion" points ; and which ensures under mild assumptions global convergence with linear convergence rate. We use i) sampling on a ball instead of Gaussian sampling (in a way inspired by trust regions), ii) an original rule for step-size adaptation ; iii) quasi-monte-carlo sampling (low dispersion points) instead of Monte-Carlo sampling. We prove in this framework linear convergence rates i) for global optimization and not only local optimization ; ii) under very mild assumptions on the regularity of the function (existence of derivatives is not required). Though the main scope of this paper is theoretical, numerical experiments are made to backup the mathematical results. Algorithm XSE: quasi-random mutations for evolution strategies. A. Auger, M. Jebalia, O. Teytaud. Proceedings of EA'2005.
Document type :
Conference papers
Complete list of metadata

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/inria-00000544
Contributor : Olivier Teytaud <>
Submitted on : Monday, February 18, 2013 - 7:06:06 PM
Last modification on : Thursday, March 5, 2020 - 6:31:38 PM
Long-term archiving on: : Sunday, May 19, 2013 - 4:06:00 AM

File

XSEshort2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00000544, version 2

Collections

Citation

Olivier Teytaud, Mohamed Jebalia, Anne Auger. Algorithms (X,sigma,eta) : quasi-random mutations for Evolution Strategies. Evolution Artificielle, 2005, Lille, France. 12 p. ⟨inria-00000544v2⟩

Share

Metrics

Record views

371

Files downloads

463