Abstract
We study the linear convergence of a simple pattern search method on non quasi-convex functions on continuous domains. Assumptions include an assumption on the sampling performed by the evolutionary algorithm (supposed to cover efficiently the neighborhood of the current search point), the conditioning of the objective function (so that the probability of improvement is not too low at each time step, given a correct step size), and the unicity of the optimum.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Auger, A.: Convergence results for (1,\(\lambda \))-SA-ES using the theory of \(\varphi \)-irreducible Markov chains. Theor. Comput. Sci. 334(1–3), 35–69 (2005)
Bergasse, R.: Stratégies d’évolution dérandomisées. Technical report, Ecole Normale Supérieure de Lyon (2007)
Beyer, H.-G., Sendhoff, B.: Covariance matrix adaptation revisited – The CMSA evolution strategy –. In: Rudolph, G., Jansen, T., Lucas, S., Poloni, C., Beume, N. (eds.) PPSN 2008. LNCS, vol. 5199, pp. 123–132. Springer, Heidelberg (2008)
Conn, A., Scheinberg, K., Toint, L.: Recent progress in unconstrained nonlinear optimization without derivatives. Math. Program. 79(1–3), 397–414 (1997)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition, vol. 31. Springer, New York (1997)
Droste, S., Jansen, T., Wegener, I.: On the optimization of unimodal functions with the (1 + 1) evolutionary algorithm. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H.-P. (eds.) PPSN 1998. LNCS, vol. 1498, p. 13. Springer, Heidelberg (1998)
Gould, N.I.M., Orban, D., Toint, P.L.: CUTEr and sifDec: A constrained and unconstrained testing environment, revisited. ACM Trans. Math. Softw. 29(4), 373–394 (2003)
Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evol. Comput. 9(2), 159–195 (2001)
Ostermeier, A., Gawelczyk, A., Hansen, N.: Step-size adaptation based on non-local use of selection informatio. In: Davidor, Y., Männer, R., Schwefel, H.-P. (eds.) PPSN 1994. LNCS, vol. 866, pp. 189–198. Springer, Heidelberg (1994)
Schwefel, H.-P.: Numerical Optimization of Computer Models. Wiley, New York (1981). 1995–2nd edn.
Back, T., Hoffmeister, F., Schewefel, H.: A survey of evolution strategies. Technical Report, Department of Computer Science XI, University of Dortmund, D-4600, Dortmund 50, Germany (1991)
Teytaud, O.: Conditionning, halting criteria and choosing lambda. In: EA07, Tours France (2007)
van der Vaart, A., Wellner, J.: Weak Convergence and Empirical Processes: Springer series in statistics. Springer, New York (1996)
Vapnik, V., Chervonenkis, A.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl. 16, 264–280 (1971)
Acknowledgements
We are grateful to Rémi Bergasse [2] for interesting discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Decock, J., Teytaud, O. (2014). Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions. In: Legrand, P., Corsini, MM., Hao, JK., Monmarché, N., Lutton, E., Schoenauer, M. (eds) Artificial Evolution. EA 2013. Lecture Notes in Computer Science(), vol 8752. Springer, Cham. https://doi.org/10.1007/978-3-319-11683-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-11683-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11682-2
Online ISBN: 978-3-319-11683-9
eBook Packages: Computer ScienceComputer Science (R0)