Abstract
This article deals with the exploitation of statistical information from extremes values of an evolutionary algorithm.
One can use the fact that upper order statistics of a sample converge to known distributions for improving efficiency of selection and crossover operators.
The work presented in this paper is restricted to criteria defined on real vector spaces. It relies on an underlying canonical model of genetic algorithm, namely tournament selection and uniform crossover. Nevertheless, the results obtained so far encourage further investigations.
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
Blickle, T.: Tournament selection. In: Handbook of Evolutionary Computation, IOP Publishing Ltd. (1997)
de Haan, L.: Estimation of the minimum of a function using order statistics. Journal of the American Statistical Association (1981)
Kallel, L., Del Moral, P., Rowe, J.: Modeling genetic algorithms with interacting particle systems. Revista de Matematica, Teoria y aplicaciones (2001)
Gonzalo, J., Olmo, J.: Which extreme values are really extremes (2003) (preprint)
Hill, B.M.: A simple approach to inference about the tail of a distribution. Annals of Statistics (1975)
Pickhands, J.: Statistical inference using extreme order statistics. Annals of Statistics (1975)
Reiss, R.D.: Approximate distributions of order statistics. Springer, Heidelberg (1989)
Zhighljavsky, A.A.: Theory of random search. Kluwer Academic Publishers, Dordrecht (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Puechmorel, S., Delahaye, D. (2004). Order Statistics in Artificial Evolution. In: Liardet, P., Collet, P., Fonlupt, C., Lutton, E., Schoenauer, M. (eds) Artificial Evolution. EA 2003. Lecture Notes in Computer Science, vol 2936. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24621-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-24621-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21523-3
Online ISBN: 978-3-540-24621-3
eBook Packages: Springer Book Archive