Costs and Benefits of Tuning Parameters of Evolutionary Algorithms

  • Volker Nannen
  • Selmar K. Smit
  • Agoston E. Eiben
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5199)


We present an empirical study on the impact of different design choices on the performance of an evolutionary algorithm (EA). Four EA components are considered—parent selection, survivor selection, recombination and mutation—and for each component we study the impact of choosing the right operator, and of tuning its free parameter(s). We tune 120 different combinations of EA operators to 4 different classes of fitness landscapes, and measure the cost of tuning. We find that components differ greatly in importance. Typically the choice of operator for parent selection has the greatest impact, and mutation needs the most tuning. Regarding individual EAs however, the impact of design choices for one component depends on the choices for other components, as well as on the available amount of resources for tuning.


Evolutionary Algorithm Shannon Entropy Parent Selection Uniform Crossover Recombination Operator 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Birattari, M.: The Problem of Tuning Metaheuristics as Seen from a Machine Learning Perspective. PhD thesis, Université Libre de Bruxelles (2004)Google Scholar
  2. 2.
    Czarn, A., MacNish, C., Vijayan, K., Turlach, B.A., Gupta, R.: Statistical Exploratory Analysis of Genetic Algorithms. IEEE Trans. Evol. Comp. 8(4), 405–421 (2004)CrossRefGoogle Scholar
  3. 3.
    Eiben, A.E., Hinterding, R., Michalewicz, Z.: Parameter Control in Evolutionary Algorithms. IEEE Trans. Evol. Comput. 3(2), 124–141 (1999)CrossRefGoogle Scholar
  4. 4.
    Eiben, A.E., Michalewicz, Z., Schoenauer, M., Smith, J.E.: Parameter Control in Evolutionary Algorithms. In: Lobo, et al. (eds.) [12], pp. 19–46Google Scholar
  5. 5.
    Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Springer, Heidelberg (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    François, O., Lavergne, C.: Design of Evolutionary Algorithms—A Statistical Perspective. IEEE Trans. Evol. Comput. 5(2), 129–148 (2001)CrossRefGoogle Scholar
  7. 7.
    Friesleben, B., Hartfelder, M.: Optimization of Genetic Algorithms by Genetic Algorithms. In: Albrecht, R.F., Reeves, C.R., Steele, N.C. (eds.) Artificial Neural Networks and Genetic Algorithms, pp. 392–399. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  8. 8.
    Gallagher, M., Yuan, B.: A General-Purpose Tunable Landscape Editor. IEEE Trans. Evol. Comput. 10(5), 590–603 (2006)CrossRefGoogle Scholar
  9. 9.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Longman Publishing Co., Boston (1989)zbMATHGoogle Scholar
  10. 10.
    Grefenstette, J.J.: Optimization of Control Parameters for Genetic Algorithms. IEEE Trans. Syst. Man Cybernet. 16(1), 122–128 (1986)CrossRefGoogle Scholar
  11. 11.
    De Jong, K.A.: An Analysis of the Behaviour of a Class of Genetic Adaptive Systems. PhD thesis, University of Michigan (1975)Google Scholar
  12. 12.
    Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.): Parameter Setting in Evolutionary Algorithms. Studies in Computational Intelligence. Springer, Heidelberg (2007)zbMATHGoogle Scholar
  13. 13.
    Luke, S., et al.: A Java-based Evolutionary Computation Research System,
  14. 14.
    Mühlenbein, H., Höns, R.: The Estimation of Distributions and the Minimum Relative Entropy Principle. Evolutionary Computation 13(1), 1–27 (2005)CrossRefGoogle Scholar
  15. 15.
    Nannen, V., Eiben, A.E.: Efficient Relevance Estimation and Value Calibration of Evolutionary Algorithm Parameters. In: IEEE Congress on Evolutionary Computation (CEC), Piscataway, NJ, USA. IEEE Press, Los Alamitos (2007)Google Scholar
  16. 16.
    Nannen, V., Eiben, A.E.: Relevance Estimation and Value Calibration of Evolutionary Algorithm Parameters. In: Veloso, M.M., et al. (eds.) Proc. of the 20th Int. Joint Conf. on Artif. Intell., IJCAI 2007, pp. 1034–1039. AAAI Press, Menlo Park (2007)Google Scholar
  17. 17.
    Oliver, I.M., Smith, D.J., Holland, J.R.C.: A Study of Permutation Crossover Operators on the Traveling Salesman Problem. In: Grefenstette, J.J. (ed.) Proc. of the 2nd Int. Conf. on Genetic Algorithms on Genetic algorithms and their application, pp. 224–230. L. E. Associates (1987)Google Scholar
  18. 18.
    Preuss, M., Bartz-Beielstein, T.: Sequential Parameter Optimization Applied to Self-adaptation for Binary-coded Evolutionary Algorithms. In: [12], pp. 91–119Google Scholar
  19. 19.
    Rudolph, G.: On Correlated Mutations in Evolution Strategies. In: Männer, R., Manderick, B. (eds.) Proc. of the 2nd Conf. on Parallel Problem Solving from Nature, pp. 107–116. Springer, Heidelberg (1992)Google Scholar
  20. 20.
    Samples, M.E., Byom, M.J., Daida, J.M.: Parameter Sweeps for Exploring Parameter Spaces of Genetic and Evolutionary Algorithms. In: [12], pp. 161–184Google Scholar
  21. 21.
    Schaffer, J.D., Caruana, R.A., Eshelman, L.J., Das, R.: A Study of Control Parameters Affecting Online Performance of Genetic Algorithms for Function Optimization. In: Schaffer, J.D. (ed.) Proc. of the 3rd Int. Conf. on Genetic Algorithms, pp. 51–60. Morgan Kaufmann, San Francisco (1989)Google Scholar
  22. 22.
    Taguchi, G., Wu, Y.: Introduction to Off-Line Quality Control. Central Japan Quality Control Association, Nagoya, Japan (1980)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Volker Nannen
    • 1
  • Selmar K. Smit
    • 1
  • Agoston E. Eiben
    • 1
  1. 1.Vrije Universiteit AmsterdamNetherlands

Personalised recommendations