Skip to main content

Some geometric and algebraic results on crossover

  • Theory and Analysis of Evolutionary Computations
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1213))

Abstract

In light of recent “No Free Lunch” theorems, crossover is neither inferior nor superior, in general, to other search operators. The present work formally establishes some properties of crossover that may be useful in analysis of when crossover performs well and when it does not. All forms of crossover which preserve the ordering of alleles are included. Alleles are restricted, however, to binary values. In this context, crossover is naturally treated as a bitwise Boolean operator parameterized by a mask indicating which alleles' values to exchange. Interesting properties of the Hamming distances between parents and offspring are derived. Several identities and inequalities of the distances are summarized in a diagram referred to as the crossover rectangle. Various algebraic properties, some counterintuitive, of crossover are also established. The algebraic definition of crossover gives rise to a simple style of formal reasoning about crossover that may prove to be generally useful.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • T. M. English (1996) “Evaluation of Evolutionary and Genetic Optimizers: No Free Lunch,” Evolutionary Programming V: Proceedings of the Fifth Annual Conference on Evolutionary Programming, L. J. Fogel, P. J. Angeline, and T. Bäck (eds.), MIT Press, Cambridge, MA, pp. 163–169.

    Google Scholar 

  • D. B. Fogel (1995) Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE Press, Piscataway, NJ.

    Google Scholar 

  • D. B. Fogel and A. Ghozeil (1996) “A Note on Representations and Variation Operators,” IEEE Transactions on Evolutionary Computation (to appear).

    Google Scholar 

  • D. E. Goldberg (1989) Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA.

    Google Scholar 

  • W. G. Macready and D. H. Wolpert (1996) “On 2-armed Gaussian Bandits and Optimization,” Santa Fe Institute, Technical Report 96-03-009.

    Google Scholar 

  • P. F. Stadler and G. P. Wagner (1996) “The Algebraic Theory of Recombination Spaces,” Santa Fe Institute, Technical Report 96-07-046.

    Google Scholar 

  • D. H. Wolpert and W. G. Macready (1995). “No Free Lunch Theorems for Search,” Santa Fe Institute, Technical Report 95-02-010.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Peter J. Angeline Robert G. Reynolds John R. McDonnell Russ Eberhart

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

English, T.M. (1997). Some geometric and algebraic results on crossover. In: Angeline, P.J., Reynolds, R.G., McDonnell, J.R., Eberhart, R. (eds) Evolutionary Programming VI. EP 1997. Lecture Notes in Computer Science, vol 1213. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014819

Download citation

  • DOI: https://doi.org/10.1007/BFb0014819

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-62788-3

  • Online ISBN: 978-3-540-68518-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics