Advertisement

The Impact of Global Structure on Search

  • Monte Lunacek
  • Darrell Whitley
  • Andrew Sutton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5199)

Abstract

Population-based methods are often considered superior on multimodal functions because they tend to explore more of the fitness landscape before they converge. We show that the effectiveness of this strategy is highly dependent on a function’s global structure. When the local optima are not structured in a predictable way, exploration can misguide search into sub-optimal regions. Limiting exploration can result in a better non-intuitive global search strategy.

Keywords

Funnel landscapes test functions exploration dynamic populations 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Eshelman, L.J.: The CHC Adaptive Search Algorithm: How to Have Safe Search When Engaging in Nontraditional Genetic Recombination. In: FOGA (1991)Google Scholar
  2. 2.
    Hansen, N., Kern, S.: Evaluating the CMA Evolution Strategy on Multimodal Test Functions. In: PPSN 2004. Springer, Heidelberg (2004)Google Scholar
  3. 3.
    Kern, S., Muller, S., Hansen, N., Buche, D., Ocenasek, J., Koumoustakos, P.: Learning Probability Distributions in Continous Evolutinary Algorithms—a Comparative Review. Natural Computing 3, 77–112 (2004)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Leary, R.H.: Global Optimization on Funneling Landscapes. Journal of Global Optimization 18 (2000)Google Scholar
  5. 5.
    Ostermeier, A., Gawelczyk, A., Hansen, N.: Step-Size Adaptation Based on Non-local use of Selection Information. In: PPSN 1994, pp. 189–198. Springer, Heidelberg (1994)Google Scholar
  6. 6.
    Pardalos, P.M., Schoen, F.: Recent Advances and Trends in Global Optimization: Deterministic and Stochastic Methods. In: CAPD (2004)Google Scholar
  7. 7.
    Wales, D.J.: Energy Landscapes and Properties of Biomolecules. Physical Biology (2005)Google Scholar
  8. 8.
    Wales, D.J., Doye, J.P.: Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms. Journal of Chemical Physics 101(28) (April 1997)Google Scholar
  9. 9.
    Whitley, D., Beveridge, R., Graves, C., Mathias, K.: Test Driving Three 1995 Genetic Algorithms: New Test Functions and Geometric Matching. Journal of Heuristics (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Monte Lunacek
    • 1
  • Darrell Whitley
    • 1
  • Andrew Sutton
    • 1
  1. 1.Colorado State UniversityFort Collins, ColoradoUSA

Personalised recommendations