Advertisement

Genetic Algorithms on NK-Landscapes: Effects of Selection, Drift, Mutation, and Recombination

  • Hernán E. Aguirre
  • Kiyoshi Tanaka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2611)

Abstract

Empirical studies have shown that the overall performance of random bit climbers on NK-Landscapes is superior to the performance of some simple and enhanced GAs. Analytical studies have also lead to suggest that NK-Landscapes may not be appropriate for testing the performance of GAs. In this work we study the effect of selection, drift, mutation, and recombination on NK-Landscapes for N = 96. We take a model of generational parallel varying mutation GA (GASRM) and switch on and off its major components to emphasize each of the four processes mentioned above. We observe that using an appropriate selection pressure and postponing drift make GAs quite robust on NK-Landscapes; different to previous studies, even simple GAs with these two features perform better than a random bit climber (RBC+) for a broad range of classes of problems (K ≥ 4). We also observe that the interaction of parallel varying mutation with crossover improves further the reliability of the GA, especially for 12 < K < 32. Contrary to intuition, we find that for small K a mutation only EA is very effective and crossover may be omitted; but the relative importance of crossover interacting with varying mutation increases with K performing better than mutation alone (K >12).We conclude that NK-Landscapes are useful for testing the GA’s overall behavior and performance and also for testing each one of the major processes involved in a GA.

Keywords

Genetic Algorithm Selection Pressure Local Search Algorithm Mutation Strategy High Optimum 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    K. A. De Jong and M. A. Potter and W. M. Spears, “Using Problem Generators to Explore the Effects of Epistasis”, Proc. 7th Int’l Conf. Genetic Algorithms, Morgan Kauffman, pp.338–345, 1997.Google Scholar
  2. 2.
    S. A. Kauffman, The Origins of Order: Self-Organization and Selection in Evolution, pp.33–67, Oxford Univ. Press, 1993.Google Scholar
  3. 3.
    Y. Davidor, “Epistasis Variance: A Viewpoint of GA-Hardness”, Proc. First Foundations of Genetic Algorithms Workshop, lMorgan Kauffman, pp.23–25, 1990.Google Scholar
  4. 4.
    B. Manderick, M. de Weger, and P. Spiessens, “The Genetic Algorithm and the Structure of the Fitness Landscape”, Proc. 4th Int’l Conf. on Genetic Algorithms, Morgan Kaufmann, pp.143–150, 1991.Google Scholar
  5. 5.
    L. Altenberg, “Evolving Better Representations through Selective Genome Growth”, Proc. 1st IEEE Conf. on Evolutionary Computation, Pistcaway, NJ:IEEE, pp.182–187, 1994.Google Scholar
  6. 6.
    J. E. Smith, Self Adaptation in Evolutionary Algorithms, Doctoral Dissertation, University of theWest of England, Bristol, 1998.Google Scholar
  7. 7.
    P. Merz and B. Freisleben, “On the Effectiveness of Evolutionary Search in High-Dimensional NK-Landscapes”, Proceedings of the 1998 IEEE International Conference on Evolutionary Computation, IEEE Press, pp. 741–745, 1998.Google Scholar
  8. 8.
    R. Heckendorn, S. Rana, and D. Whitley, “Test Function Generators as Embedded Landscapes”, Foundations of Genetic Algorithms 5, Morgan Kaufmann, pp.183–198, 1999.Google Scholar
  9. 9.
    K. E. Mathias, L. J. Eshelman, and D. Schaffer, “Niches in NK-La ndscapes”, Foundations of Genetic Algorithms 6, Morgan Kaufmann, pp.27–46, 2000.Google Scholar
  10. 10.
    M. Shinkai, H. Aguirre, and K. Tanaka, “Mutation Strategy Improves GA’s Performance on Epistatic Problems”, Proc. 2002 IEEE World Congress on Computational Intelligence, pp.795–800, 2002.Google Scholar
  11. 11.
    L. J. Eshelman, “The CHC Adaptive Search Algorithm: How to Have a Save Search When Engaging in Nontraditional Genetic Recombination”, Foundations of Genetic Algorithms, Morgan Kaufmann, pp.265–283, 1991.Google Scholar
  12. 12.
    L. Davis, “Bit-Climbing, Representational Bias, and Test Suite Design”, Proc. 4th Int’l Conf. on Genetic Algorithms, Morgan Kaufman, pp.18–23, 1991.Google Scholar
  13. 13.
    L. Altenberg, “Fitness Landscapes: NK Landscapes”, Handbook of Evolutionary Computation, Institute of Physics Publishing & Oxford Univ. Press, pp. B2.7:5–10, 1997.Google Scholar
  14. 14.
    R. E. Smith and J. E. Smith, “An examination of Tunable, Random Search Landscapes”, Foundations of Genetic Algorithms 5, Morgan Kaufmann, pp.165–182, 1999.Google Scholar
  15. 15.
    R. E. Smith and J. E. Smith, “New Methods for Tunable, Random Landscapes”, Foundations of Genetic Algorithms 6, Morgan Kaufmann, pp.47–67, 2001.CrossRefGoogle Scholar
  16. 16.
    H. Aguirre, K. Tanaka, and T. Sugimura. Cooperative Model for Genetic Operators to Improve GAs. In Proc. IEEE Int’l Conf. on Information, Intelligence, and Systems, pp.98–106, 1999.Google Scholar
  17. 17.
    H. Aguirre, K. Tanaka, T. Sugimura, and S. Oshita. Cooperative-Competitive Model for Genetic Operators: Contributions of Extinctive Selection and Parallel Genetic Operators. In Proc. Late Breaking Papers Genetic and Evolutionary Computation Conference, Morgan Kaufmann, pp.6–14, 2000.Google Scholar
  18. 18.
    T. Bäck, Evolutionary Algorithms in Theory and Practice, Oxford Univ. Press, 1996.Google Scholar
  19. 19.
    D. Whitley, “The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best”, Proc. Third Intl. Conf. on Genetic Algorithms, Morgan Kauffman, pp. 116–121, 1989.Google Scholar
  20. 20.
    D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning,Addison-Wesley, 1989.Google Scholar
  21. 21.
    L. Eshelman and D. Schaffer, “Preventing Premature Convergence in Genetic Algorithms by Preventing Incest”, Fourth Intl. Conf. on Genetic Algorithms, Morgan Kauffman, pp.115–122, 1991.Google Scholar
  22. 22.
    D. Schaffer, M. Mani, L. Eshelman, and K. Mathias, “The Effect of Incest Prevention on Genetic Drift”, Foundations of Genetic Algorithms 5, Morgan Kaufmann, pp.235–243, 1999.Google Scholar
  23. 23.
    K.-H. Liang, X. Yao, C. Newton and D. Hoffman, “Solving Cutting Stock Problems by Evolutionary Programming”, Evolutionary Programming VII: Proc. of the Seventh Annual Conference on Evolutionary Programming (EP98), Lecture Notes in Computer Science, Springer-Verlag, vol. 1447, pp.291–300, 1998.Google Scholar
  24. 24.
    J. He and X. Yao, “From an Individual to a Population: An Analysis of the First Hitting Time of Population-Based Evolutionary Algorithms,” IEEE Transactions on Evolutionary Computation, 6(5):495–511, 2002.CrossRefGoogle Scholar
  25. 25.
    C.R. Reeves and J.E. Rowe, Genetic Algorithms–Principles and Perspectives, Kluwer, Norwell, MA, 2002.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Hernán E. Aguirre
    • 1
  • Kiyoshi Tanaka
    • 1
  1. 1.Faculty of EngineeringShinshu UniversityNaganoJapan

Personalised recommendations