28972 articles – 22398 references  [version française]

inria-00494478, version 1

## 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

Parallel Problem Solving From Nature (PPSN2010) (2010) xxxx-xxx

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.

• 1:  TAO (INRIA Saclay - Ile de France)
• INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
• Domain : Mathematics/Optimization and Control

• inria-00494478, version 1
• oai:hal.inria.fr:inria-00494478
• From:
• Submitted on: Thursday, 24 June 2010 11:19:29
• Updated on: Thursday, 1 July 2010 11:14:35