Abstract
The role of crossover and mutation in Genetic Programming (GP) has been the subject of much debate since the emergence of the field. In this paper, we contribute new empirical evidence to this argument using a rigorous and principled experimental method applied to six problems common in the GP literature. The approach tunes the algorithm parameters to enable a fair and objective comparison of two different GP algorithms, the first using a combination of crossover and reproduction, and secondly using a combination of mutation and reproduction. We find that crossover does not significantly outperform mutation on most of the problems examined. In addition, we demonstrate that the use of a straightforward Design of Experiments methodology is effective at tuning GP algorithm parameters.
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
Luke, S., Spector, L.: A comparison of crossover and mutation in genetic programming. In: Genetic Programming 1997: Proceedings of the Second Annual Conference, pp. 240–248. Morgan Kaufmann, San Francisco (1997)
Luke, S., Spector, L.: A revised comparison of crossover and mutation in genetic programming. In: Genetic Programming 1998: Proceedings of the Third Annual Conference, pp. 208–213. Morgan Kaufmann, San Francisco (1998)
Angeline, P.J.: Comparing subtree crossover with macromutation. In: Angeline, P.J., McDonnell, J.R., Reynolds, R.G., Eberhart, R. (eds.) EP 1997. LNCS, vol. 1213, pp. 101–112. Springer, Heidelberg (1997)
Montgomery, D.C.: Design and Analysis of Experiments, 6th edn. John Wiley & Sons, Inc., Chichester (2005)
Johnson, D.S.: A theoretician’s guide to the experimental analysis of algorithms. In: Goldwasser, M.H., Johnson, D.S., McGeoch, C.C. (eds.) Data Structures, Near Neighbor Searches, and Methodology: Fifth and Sixth DIMACS Implementation Challenges, pp. 215–250. American Mathematical Society, Providence (2002)
Online Experiment Source Code and Scripts, http://www.cs.york.ac.uk/~drw/papers/eurogp2009/
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)
Feldt, R., Nordin, P.: Using factorial experiments to evaluate the effect of genetic programming parameters. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds.) EuroGP 2000. LNCS, vol. 1802, pp. 271–282. Springer, Heidelberg (2000)
Coy, S.P., Golden, B.L., Runger, G.C., Wasil, E.A.: Using experimental design to find effective parameter settings for heuristics. Journal of Heuristics 7(1), 77–97 (2001)
ECJ (2008), http://cs.gmu.edu/~eclab/projects/ecj/
Koza, J.R.: Genetic Programming II: Automatic Discovery of Reusable Programs. MIT Press, Cambridge (1994)
Myers, R.H., Montgomery, D.C.: Response surface methodology: process and product optimization using designed experiments. Wiley Series in Probability and Statistics. John Wiley & Sons, Inc., Chichester (2005)
Vadde, K.K., Syrotiuk, V.R., Montgomery, D.C.: Optimizing protocol interaction using response surface methodology. IEEE Trans. Mob. Comput. 5(6), 627–639 (2006)
Leech, N.L., Onwuegbuzie, A.J.: A call for greater use of nonparametric statistics. Technical report, US Dept. Education, Educational Resources Information Center (2002)
Wilcoxon, F.: Individual comparisions by ranking methods. Biometrics Bulletin 1(6), 80–83 (1945)
Vargha, A., Delaney, H.: A critique and improvement of the CL common language effect size statistics of McGraw and Wong. J. Educational and Behavioral Statistics 25(2), 101–132 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
White, D.R., Poulding, S. (2009). A Rigorous Evaluation of Crossover and Mutation in Genetic Programming. In: Vanneschi, L., Gustafson, S., Moraglio, A., De Falco, I., Ebner, M. (eds) Genetic Programming. EuroGP 2009. Lecture Notes in Computer Science, vol 5481. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01181-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-01181-8_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01180-1
Online ISBN: 978-3-642-01181-8
eBook Packages: Computer ScienceComputer Science (R0)