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

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 : Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this paper, 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 :
Conference papers

Cited literature [17 references]

https://hal.inria.fr/inria-00494478
Contributor : Mohamed Jebalia <>
Submitted on : Thursday, June 24, 2010 - 11:19:29 AM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Monday, October 22, 2012 - 2:42:03 PM

### File

ppsn2010JebaliaAuger.pdf
Files produced by the author(s)

### Identifiers

• HAL Id : inria-00494478, version 1

### 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. Parallel Problem Solving From Nature (PPSN2010), Sep 2010, Krakow, Poland. pp.xxxx-xxx. ⟨inria-00494478⟩

Record views