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.