Advertisement

A critical and empirical study of epistasis measures for predicting GA performances: A summary

  • S. Rochet
  • G. Venturini
  • M. Slimane
  • E. M. El Kharoubi
Methodologies
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1363)

Abstract

Epistasis measures have been developed for measuring statistical information about the difficulty of a function to be optimized by a genetic algorithm (GA). We give first a review of the work on these measures such as the epistasis correlation. Then we try to relate the epistasis correlation to the overall performances of a binary GA on a set of 14 functions. The only relation that seems to hold strongly is that a high epistasis correlation implies GA-easy, as indicated by the GA theory of deceptiveness. Then, we show that changing the representation of the search space with transformations that improve epistasis measures does not imply the same increasing in the genetic algorithm performances. These both empirical studies seem to indicate that the generality of epistasis measures is limited.

Keywords

Genetic Algorithm Search Space Fitness Function Lookup Table Binary String 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ackley D.H. (1987), A connectionist machine for genetic hillclimbing, Boston, MA: Kluwer Academic.Google Scholar
  2. Davidor Y. (1991). Epistasis Variance: A Viewpoint on GA-Hardness. In Foundations of Genetic Algorithms. Gregory J. E. Rawlins (Ed). Morgan Kaufmann Publishers, San Mateo. pp 23–35.Google Scholar
  3. Goldberg D.E. (1987), Simple genetic algorithms and the minimal deceptive problem, Genetic Algorithms and Simulated Annealing, L. Davis (Ed), Morgan Kaufmann, pp 74–88.Google Scholar
  4. Goldberg D.E., Korb B. et Deb K. (1989), Messy genetic algorithms: motivations, analysis, and first results. Complex systems 4, pp 415–444.Google Scholar
  5. Grefenstette J.J. (1992), Deception considered harmful, Proceedings of the second workshop on Foundations of Genetic Algorithms, 1992, D. Whitley (Ed), Morgan Kaufmann, pp 75–91.Google Scholar
  6. Grefenstette J. J. (1995). Predictive Models Using Fitness Distributions of Genetic Operators. In Foundation of Genetic Algorithms 3. D. Whitley and M. Vose (Eds), Morgan Kaufmann, San Mateo, CA.Google Scholar
  7. Holland J.H. (1975), Adaptation in natural and artificial systems. Ann Arbor: University of Michigan Press.Google Scholar
  8. Jones T. and Forrest S. (1995), Fitness distance correlation as a measure of problem difficulty for genetic algorithms, Proceedings of the Sixth International Conference on Genetic Algorithms, 1995, L.J. Eshelman (Ed), Morgan Kaufmann, pp 184-192.Google Scholar
  9. Liepins G. E., Vose M.D. (1990). Representationnal issues in genetic optimization. Journal of Experimental and Theoretical Artificial Intelligence 2 Research paper, pp 101–115.Google Scholar
  10. Manderick B., de Weger M. and Spiessens P. (1991), The genetic algorithm and the structure of the fitness landscape, Proceedings of the Fourth International Conference on Genetic Algorithms, 1991, R.K. Belew and L.B. Booker (Eds), Morgan Kaufmann, pp 143–150.Google Scholar
  11. Manela M. and Campbell J.A. (1992), Harmonic analysis, epistasis and genetic algorithms, Proceedings of the Second Conference on Parallel Problem Solving from Nature 1992, R. Manner et B. Manderick (Eds), Elsevier, pp 57–64.Google Scholar
  12. Reeves C.R., Wright C. C. (1995). Epistasis in Genetic Algorithms: An Experimental Design Perspective. Proceedings of the sixth International Conference on Genetic Algorithms. Larry J. Eshelman (Ed), Morgan Kaufmann, San Mateo, CA. pp 217–224.Google Scholar
  13. Rochet S. (1997). Epistasis in genetic algorithms revisited. To appear in Information Sciences.Google Scholar
  14. Rochet S., Slimane M. and Venturini G. (1996), Epistasis for real encoding in genetic algorithms, IEEE ANZIIS'96, V. L. Narasimhan and L. C. Jain (eds), Australia, pp. 268–271.Google Scholar
  15. Rochet S., G. Venturini, M. Slimane (1997), A critical study of epistasis measures, in preparation.Google Scholar
  16. Soule T. and Foster J.A. (1997), Genetic algorithm hardness measures applied to the maximum clique problem, Proceedings of the seventh International Conference on Genetic Algorithms, 1997, T. Baeck (Ed.), Morgan Kaufmann, pp 81–88.Google Scholar
  17. Venturini G., Rochet S. and Slimane M. (1997), Schemata and deception in binary genetic algorithms: a tutorial, to appear in Control and Cybernetics, Special Issue on Evolutionary Algorithms, M. Schoenauer and Z. Michalewicz (Eds).Google Scholar
  18. Whitley D. (1991), Fundamental principles of deception in genetic search, Proceedings of the first Workshop on Foundations of Genetic Algorithms, 1991, G.J.E. Rawlins (Ed), Morgan Kaufmann, pp 221–241.Google Scholar
  19. Whitley D., Mathias K., Rana S. and Dzubera J. (1995), Building better test functions, Proceedings of the Sixth International Conference on Genetic Algorithms, Eshelman L.J. (ed), Morgan Kaufmann publishers, pp. 239–246.Google Scholar
  20. Wilson S.W. (1991), GA-easy does not imply steepest-ascent optimizable, Proceedings of the Fourth International Conference on Genetic Algorithms, 1991, R.K. Belew and L.B. Booker (Eds), Morgan Kaufmann, pp 85–89.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • S. Rochet
    • 1
  • G. Venturini
    • 2
  • M. Slimane
    • 2
  • E. M. El Kharoubi
    • 2
  1. 1.IUTDép. Génie ElectriqueSalon de ProvenceFrance
  2. 2.Laboratoire d'informatiqueUniversité de ToursToursFrance

Personalised recommendations

Cite paper

Buy options