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).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
M. I. Freidlin, A. D. Wentzell, “Random perturbations of dynamical systems.” Trad, de: “Fluktuatsii u Dinamicheskikh Sistemakh Pod Deistviem Malykh Sluchainykh Vozmushchenii”. Springer, 1984.
M. Jerrum, “Mathematical Foundations of the Markov Chain Monte Carlo Method”. In M. Habib, C. McDiarmid, J. Ramirez-Alfonsin, B. Reed (Eds.), Probabilistic Methods for Algorithmic Discrete Mathematics, Springer Verlag, 1998.
E. Aarts and P. Van Laarhoven, “Simulated annealing: a pedestrian review of the theory and some applications”. NATO, ASI Series, Vol. F30, Springer Verlag.
E. Lutton and J. Lévy Véhel, Some remarks on the optimization of Hölder functions with Genetic Algorithms, IEEE trans on Evolutionary computing, 1998, see also Inria Research Report No 2627.
B. Leblanc, and E. Lutton. Bitwise Regularity Coefficients as a Tool for Deception Analysis of a Genetic Algorithm, 1997, INRIA research report, RR-3274.
A. Agapie. Genetic algorithms: Minimal conditions for convergence. In Artificial Evolution, European Conference, AE 97. Nimes, France, October 1997,. Springer Verlag, 1997.
Lee Altenberg. The Schema Theorem and Price’s Theorem. In Foundation of Genetic Algorithms 3, 1995. ed. Darrell Whitley and Michael Vose. pp. 23–49. Morgan Kaufmann, San Francisco.
R. Cerf. Artificial Evolution, European Conference, AE 95, Brest, France, September 1995, Selected papers, volume Lecture Notes in Computer Science 1063, chapter Asymptotic convergence of genetic algorithms, pages 37–54. Springer Verlag, 1995.
Thomas E. Davis and Jose C. Principe. A Simulated Annealing Like Convergence Theory for the Simple Genetic Algorithm. In Proceedings of the Fourth International Conference on Genetic Algorithm, pages 174–182, 1991. 13–16 July.
O. François “An Evolutionary Strategy for Global Minimization and its Markov Chain Analysis IEEE transactions on evolutionary computation, septembre 1998
Evelyne Lutton. Genetic Algorithms and Fractals. In Evolutionary Algorithms in Engineering and Computer Science, K. Mietttinen, M. M. Mäkelä, P. Neittaan-maki, J. Périaux, Eds, John Wiley & Sons, 1999.
G. Rudolph. Asymptotical convergence rates of simple evolutionary algorithms under factorizing mutation distributions. In Artificial Evolution, European Conference, AE 97, Nimes, France, October 1997,. Springer Verlag, 1997.
A. Trouvé, Rough large deviation estimates for the optimal convergence speed exponent of generalized simulated annealing algorithms. 1993
M.D. Vose. Formalizing genetic algorithms. In Genetic Algorithms, Neural Networks and Simulated Annealing Applied to Problems in Signal, and Image processing. The institute of Electrical and Electronics Engineers Inc., 8th–9th May 1990. Kelvin Conference Centre, University of Glasgow.
Y. Landrin-Schweitzer, E. Lutton. Perturbation theory for Evolutionary Algorithms. Inria Research Report, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Landrin-Schweitzer, Y., Lutton, E. (2000). Perturbation Theory for Evolutionary Algorithms: Towards an Estimation of Convergence Speed. In: Schoenauer, M., et al. Parallel Problem Solving from Nature PPSN VI. PPSN 2000. Lecture Notes in Computer Science, vol 1917. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45356-3_11
Download citation
DOI: https://doi.org/10.1007/3-540-45356-3_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41056-0
Online ISBN: 978-3-540-45356-7
eBook Packages: Springer Book Archive