Perturbation Theory for Evolutionary Algorithms: Towards an Estimation of Convergence Speed

Authors:
Yann Landrin-Schweitzer;Evelyne Lutton
Affiliations:
-;-
Venue:
PPSN VI Proceedings of the 6th International Conference on Parallel Problem Solving from Nature
Year:
2000

Citing 4
Cited 1

An Asymptotic Theory of Genetic Algorithms

AE '95 Selected Papers from the European conference on Artificial Evolution
Genetic Algorithms: Minimal Conditions for Convergence

AE '97 Selected Papers from the Third European Conference on Artificial Evolution
Asymptotical Convergence Rates of Simple Evolutionary Algorithms under Factorizing Mutation Distributions

AE '97 Selected Papers from the Third European Conference on Artificial Evolution
An evolutionary strategy for global minimization and its Markovchain analysis

IEEE Transactions on Evolutionary Computation

Algorithms (x, sigma, eta): quasi-random mutations for evolution strategies

EA'05 Proceedings of the 7th international conference on Artificial Evolution

Quantified Score

Hi-index	0.00

Visualization

Abstract

When considering continuous spaces EA, a convenient tool to model these algorithms is perturbation theory. In this paper we present preliminary results, derived from Freidlin-Wentzell theory, related to the convergence of a simple EA model. The main result of this paper yields a bound on sojourn times of the Markov process in subsets centered around the maxima of the fitness function. Exploitation of this result opens the way to convergence speed bounds with respect to some statistical measures on the fitness function (likely related to irregularity).