Abstract
A hybrid approach that combines the (1+1)-ES and threshold selection methods is developed. The framework of the new experimentalism is used to perform a detailed statistical analysis of the effects that are caused by this hybridization. Experimental results on the sphere function indicate that hybridization worsens the performance of the evolution strategy, because evolution strategies are well-scaled hill-climbers: the additional threshold disturbs the self-adaptation process of the evolution strategy. Theory predicts that the hybrid approach might be advantageous in the presence of noise. This effect could be observed—however, a proper fine tuning of the algorithm’s parameters appears to be advantageous.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hoos, H.H., Stützle, T.: Stochastic Local Search—Foundations and Applications. Elsevier, Amsterdam (2005)
Mayo, D.G.: Error and the Growth of Experimental Knowledge. The University of Chicago Press, Chicago (1996)
Bartz-Beielstein, T., Markon, S.: Tuning search algorithms for real-world applications: A regression tree based approach. In: Greenwood, G.W. (ed.) Proc. 2004 Congress on Evolutionary Computation (CEC 2004), Portland OR, vol. 1, pp. 1111–1118. IEEE Press, Piscataway (2004)
Bartz-Beielstein, T., Parsopoulos, K.E., Vrahatis, M.N.: Design and analysis of optimization algorithms using computational statistics. Applied Numerical Analysis & Computational Mathematics (ANACM) 1(2), 413–433 (2004)
Lasarczyk, C., Banzhaf, W.: Total synthesis of algorithmic chemistries. In: GECCO 2005: Proceedings of the Genetic and Evolutionary Computation Conference (2005) (in print)
Bartz-Beielstein, T., Lasarczyk, C., Preuss, M.: Sequential parameter optimization. In: Proc. 2005 Congress on Evolutionary Computation (CEC 2005), Edinburgh. IEEE Press, Piscataway (2005) (in print)
Schwefel, H.-P.: Evolution and Optimum Seeking. ser. Sixth-Generation Computer Technology. Wiley Interscience, New York (1995)
Hacking, I.: Representing and intervening. Cambridge University Press, Cambridge (1983)
Rechenberg, I.: Evolutionsstrategie. Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. frommann-holzboog, Stuttgart (1973)
Markon, S., Arnold, D.V., Bäck, T., Beielstein, T., Beyer, H.-G.: Thresholding – A selection operator for noisy ES. In: Kim, J.-H., Zhang, B.-T., Fogel, G., Kuscu, I. (eds.) Proc. 2001 Congress on Evolutionary Computation (CEC 2001), Seoul, pp. 465–472. IEEE Press, Piscataway (2001)
Matyáš, J.: Random Optimization. Automation and Remote Control 26(2), 244–251 (1965)
Stewart, E.C., Kavanaugh, W.P., Brocker, D.H.: Study of a global search algorithm for optimal control. In: Proceedings of the 5th International Analogue Computation Meeting, Lausanne, pp. 207–230 (August-September1967)
Dueck, G., Scheuer, T.: Threshold accepting: a general purpose optimization algorithm appearing superior to simulated annealing. Journal of Computational Physics 90, 161–175 (1990)
Bartz-Beielstein, T.: New experimentalism applied to evolutionary computation. Ph.D. dissertation, University of Dortmund (April 2005)
Hoos, H.H.: Stochastic local search – methods, models, applications. Ph.D. dissertation, Technische Universität Darmstadt (1998)
Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the Nelder–Mead simplex method in low dimensions. SIAM J. on Optimization 9(1), 112–147 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bartz-Beielstein, T. (2005). Evolution Strategies and Threshold Selection. In: Blesa, M.J., Blum, C., Roli, A., Sampels, M. (eds) Hybrid Metaheuristics. HM 2005. Lecture Notes in Computer Science, vol 3636. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11546245_10
Download citation
DOI: https://doi.org/10.1007/11546245_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28535-9
Online ISBN: 978-3-540-31898-9
eBook Packages: Computer ScienceComputer Science (R0)