Abstract
Fitness Distance Correlation has been proposed as a measure of function optimization difficulty. This paper describes a class of functions, named the Ridge Functions which, according to the measure, should be highly misleading. However, all functions tested were optimized easily by both a GA and a simple hill climbing algorithm. Scatter graph analysis of Ridge functions gave little guidance due to the large number of functions with an identical scatter graph, the majority of which are not in the class of Ridge functions and are not simple to optimize.
Preview
Unable to display preview. Download preview PDF.
References
L. Altenberg. Fitness distance correlation analysis: An instructive counterexample. In Proceedings of the Seventh International Conference on Genetic Algorithms, pages 57–64. Morgan Kaufmann, 1997.
D. E. Goldberg J. Horn and K. Deb. Long path problems. In Parallel Problem Solving from Nature. Springer, 1994.
L. Kallel and M. Schoenauer. A priori comparison of binary crossover operators: No universal statistical measure, but a set of hints. In Proceedings of the third Artificial Evolution, pages 287–299. Springer, 1997.
B. Naudts and L. Kallel. Some facts about so called GA-hardness measures. Technical report, University of Antwerp, 1998.
V. J. Rayward-Smith R. J. Quick and G. D. Smith. Ridge functions. Technical Report 98-005, University of East Anglia, 1998.
T.Jones. Evolutionary Algorithms, Fitness Landscapes and Search. PhD thesis, Massachusetts Institute of Technology, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Quick, R.J., Rayward-Smith, V.J., Smith, G.D. (1998). Fitness distance correlation and Ridge functions. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, HP. (eds) Parallel Problem Solving from Nature — PPSN V. PPSN 1998. Lecture Notes in Computer Science, vol 1498. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0056851
Download citation
DOI: https://doi.org/10.1007/BFb0056851
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65078-2
Online ISBN: 978-3-540-49672-4
eBook Packages: Springer Book Archive