Log-linear Convergence of the Scale-invariant $(\mu/\mu_w,\lambda)$-{ES} and Optimal mu for Intermediate Recombination for Large Population Sizes

Mohamed Jebalia 1 Anne Auger 1
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this report, we study the convergence of the (mu/mu_w,lambda)-ES, an ES with weighted recombination, and derive its optimal convergence rate and optimal mu especially for large population sizes. First, we theoretically prove the log-linear convergence of the algorithm using a scale-invariant adaptation rule for the step-size and minimizing spherical objective functions and identify its convergence rate as the expectation of an underlying random variable. Then, using Monte-Carlo computations of the convergence rate in the case of equal weights, we derive optimal values for mu that we compare with previously proposed rules. Our numerical computations show also a dependency of the optimal convergence rate in ln(lambda) in agreement with previous theoretical results.
Document type :
Reports
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/inria-00495401
Contributor : Mohamed Jebalia <>
Submitted on : Friday, June 25, 2010 - 7:15:31 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Monday, October 22, 2012 - 2:51:02 PM

File

RR-7275.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00495401, version 1

Collections

Citation

Mohamed Jebalia, Anne Auger. Log-linear Convergence of the Scale-invariant $(\mu/\mu_w,\lambda)$-{ES} and Optimal mu for Intermediate Recombination for Large Population Sizes. [Research Report] RR-7275, INRIA. 2010. ⟨inria-00495401⟩

Share

Metrics

Record views

397

Files downloads

175