Convergence results for the (1, γ)-SA-ES using the theory of φ-irreducible Markov chains

Theoretical Computer Science

Volumn 334, Issue 1-3, 2005, Pages 35-69

  Auger, Anne ^a,b  

^a INRIA   (France)

^b ETH ZURICH   (Switzerland)

Author keywords

Convergence; Evolution strategies; Foster Lyapunov drift conditions; Markov chains

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; EVOLUTIONARY ALGORITHMS; FUNCTIONS; LYAPUNOV METHODS; MATHEMATICAL OPERATORS; OPTIMIZATION; SET THEORY; VECTORS;

CONVERGENCE; EVOLUTION STRATEGIES; FOSTER-LYAPUHOV DRIFT CONDITIONS; GAUSSIAN VECTOR;

MARKOV PROCESSES;

EID: 16344383127     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.tcs.2004.11.017     Document Type: Article

References (22)

1. C. Andrieu, and A. Doucet Convergence of simulated annealing using Foster-Lyapunov criteria J. Appl. Probab. 38 2001 975 994
2. A. Benveniste, M. Métiver, P. Priouret, Algorithmes adaptatifs et approximations stochastiques, 1987.
3. H.-G. Beyer Towards a theory of evolution strategies self-adaptation Evol. Comput. 3 3 1995 311 347
4. H.-G. Beyer The Theory of Evolution Strategies 2001 Springer Heidelberg
5. A. Bienvenüe, and O. Franĉois Global convergence for evolution strategies in spherical problems some simple proofs and difficulties Theoret. Comput. Sci. A 306 1-3 2003 269 289
6. P. Billingsley Probability and Measure 1986 Wiley New York
7. J.M. DeLaurentis, L.A. Ferguson, and W.E. Hart On the convergence properties of a simple self-adaptive evolutionary algorithm W.B. Langdon Proc. Genetic and Evolutionary Conf. 2002 Morgan Kaufmann Los Altos, CA 229 237
8. M. Duflo Algorithmes Stochastiques 1996 Springer-Verlag Paris
9. C.J. Geyer Practical Markov chain Monte Carlo Statist. Sci. 7 4 1993 473 511
10. N. Hansen, S. Müller, and P. Koumoutsakos Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES) Evol. Comput. 11 1 2003 1 18
11. N. Hansen, and A. Ostermeier Adapting arbitrary normal mutation distributions in evolution strategies the covariance matrix adaption Proc. Third IEEE Int. Conf. on Evolutionary Computation 1996 IEEE Press New York 312 317
12. N. Hansen, and A. Ostermeier Completely derandomized self-adaptation in evolution strategies Evol. Comput. 9 2 2001 159 195
13. S.P. Meyn, and R.L. Tweedie Markov Chains and Stochastic Stability 1993 Springer-Verlag New York
14. A. Ostermeier, A. Gawelczyk, and N. Hansen A derandomized approach to self adaptation of evolution strategies Evol. Comput. 2 4 1995 369 380
15. I. Rechenberg Evolutionstrategie Optimierung Technisher Systeme nach Prinzipien des Biologischen Evolution 1973 Fromman-Hozlboog Verlag Stuttgart
16. C.P. Robert Convergence control techniques for Markov chain Monte Carlo algorithms Statist. Sci. 10 3 1996 231 253
17. G. Roberts, and R. Tweedie Geometric convergence and central limit theorems for multidimensional hasting and metropolis algorithms Biometrika 83 1996 96 110
18. G. Roberts, and R. Tweedie Exponential convergence of langevin diffusions and their discrete approximations Bernoulli 2 1997 314 363
19. B.W. Schmeiser Batch size effects in the analysis of simulation outputs Oper. Res. 30 1982 556 568
20. H.-P. Schwefel, Numerical Optimization of Computer Models, second ed., Wiley, New York, 1981, 1995.
21. M.A. Semenov Convergence velocity of an evolutionary algorithm with self-adaptation W.B. Langdon Proc. Genetic and Evolutionary Conf. 2002 Morgan Kaufmann Los Altos, CA 210 213
22. M.A. Semenov, and D.A. Terkel Analysis of convergence of an evolutionary algorithm with self-adaptation using a stochastic Lyapunov function Evol. Comput. 11 4 2003 363 380