Abstract
We investigate the adaptability of optimization algorithms for the real-valued case to concrete problems via tuning. However, the focus is not primarily on performance, but on the tuning potential of each algorithm/problem system, for which we define the empirical tuning potential measure (ETP). It is tested if this measure fulfills some trivial conditions for usability, which it does. We also compare the best obtained configurations of 4 adaptable algorithms (2 evolutionary, 2 classic) with classic algorithms under default settings. The overall outcome is quite mixed: Sometimes adapting algorithms is highly profitable, but some problems are already solved to optimality by classic methods.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
- Adaptable Algorithm
- Latin Hypercube Sample
- Tuning Method
- Tuning Process
- Covariance Matrix Adaptation Evolution Strategy
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.
References
Auger, A., Hansen, N.: A Restart CMA Evolution Strategy With Increasing Population Size. In: McKay, B., et al. (eds.) Proc. 2005 Congress on Evolutionary Computation (CEC 2005), Piscataway NJ, pp. 1769–1776. IEEE Press, Los Alamitos (2005)
Bartz-Beielstein, T.: Experimental Research in Evolutionary Computation – The New Experimentalism. Natural Computing Series. Springer, Berlin (2006)
Bartz-Beielstein, T., Preuss, M.: Considerations of Budget Allocation for Sequential Parameter Optimization (SPO). In: Paquete, L., Chiarandini, M., Basso, D. (eds.) Empirical Methods for the Analysis of Algorithms, Workshop EMAA 2006, Proceedings, Reykjavik, Iceland, pp. 35–40 (2006)
Belisle, C.J.P.: Convergence theorems for a class of simulated annealing algorithms on \(\mathbb R^d\). Annals of Applied Probability 29, 885–895 (1992)
Beyer, H.-G., Schwefel, H.-P.: Evolution strategies: A comprehensive introduction. Natural Computing 1(1), 3–52 (2002)
Birattari, M., Stützle, T., Paquete, L., Varrentrapp, K.: A racing algorithm for configuring metaheuristics. In: Langdon, W.B., et al. (eds.) Proc. Genetic and Evolutionary Computation Conf. (GECCO 2002). Morgan Kaufmann, San Francisco (2002)
Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM Journal on Scientific Computing 16, 1190–1208 (1995)
Clausen, A.: An implementation of the bfgs algorithm for smooth function minimization (2007), http://www.econ.upenn.edu/~clausen/computing/bfgs.zip
Eiben, A.E., Jelasity, M.: A critical note on experimental research methodology in EC. In: Proceedings of the 2002 Congress on Evolutionary Computation (CEC 2002), pp. 582–587. IEEE Press, Los Alamitos (2002)
Hansen, N., Ostermeier, A.: Completely Derandomized Self-Adaptation in Evolution Strategies. IEEE Computational Intelligence Magazine 9(2), 159–195 (2001)
Jong, K.D.: Parameter setting in eas: a 30 year perspective. In: Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.) Parameter Setting in Evolutionary Algorithms. Springer, Berlin (2007)
Nash, J.C.: Compact Numerical Methods for Computers: Linear Algebra and Function Minimisation, 2nd edn. IOP, Bristol (1990)
Nelder, J.A., Mead: A simplex method for function minimization. The Computer Journal (7), 308–313 (1965)
Schwefel, H.-P.: Direct search for optimal parameters within simulation models. In: Conine, R.D., et al. (eds.) Proc. Twelfth Annual Simulation Symp., Tampa FL, Long Beach, CA, pp. 91–102. IEEE Computer Society, Los Alamitos (1979)
Suganthan, P.N., Hansen, N., Liang, J.J., Deb, K., Chen, Y.-P., Auger, A., Tiwari, S.: Problem definitions and evaluation criteria for the cec 2005 special session on real-parameter optimization. Technical report, Nanyang Technological University, Singapore (May 2005), http://www.ntu.edu.sg/home/EPNSugan
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
Preuss, M. (2009). Adaptability of Algorithms for Real-Valued Optimization. In: Giacobini, M., et al. Applications of Evolutionary Computing. EvoWorkshops 2009. Lecture Notes in Computer Science, vol 5484. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01129-0_76
Download citation
DOI: https://doi.org/10.1007/978-3-642-01129-0_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01128-3
Online ISBN: 978-3-642-01129-0
eBook Packages: Computer ScienceComputer Science (R0)