Skip to main content
SpringerLink
Log in

Log-Linear Convergence and Divergence of the Scale-Invariant (1+1)-ES in Noisy Environments

  • Published:
Algorithmica Aims and scope Submit manuscript

Abstract

Noise is present in many real-world continuous optimization problems. Stochastic search algorithms such as Evolution Strategies (ESs) have been proposed as effective search methods in such contexts. In this paper, we provide a mathematical analysis of the convergence of a (1+1)-ES on unimodal spherical objective functions in the presence of noise. We prove for a multiplicative noise model that for a positive expected value of the noisy objective function, convergence or divergence happens depending on the infimum of the support of the noise. Moreover, we investigate convergence rates and show that log-linear convergence is preserved in presence of noise. This result is a strong theoretical foundation of the robustness of ESs with respect to noise.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Nissen, V., Propach, J.: On the robustness of population-based versus point-based optimization in the presence of noise. IEEE Trans. Evol. Comput. 2(3), 107–119 (1998)

    Article  Google Scholar 

  2. Arnold, D.V., Beyer, H.-G.: A comparison of evolution strategies with other direct search methods in the presence of noise. Comput. Optim. Appl. 24, 135–159 (2003)

    Article  MATH  MathSciNet  Google Scholar 

  3. Jin, Y., Branke, J.: Evolutionary optimization in uncertain environments—a survey. IEEE Trans. Evol. Comput. 9(3), 303–317 (2005)

    Article  Google Scholar 

  4. Arnold, D.V.: Noisy Optimization with Evolution Strategies. GENA. Kluwer Academic, Dordrecht (2002)

    MATH  Google Scholar 

  5. 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 and KanGAL Report Number 2005005 (Kanpur Genetic Algorithms Laboratory, IIT Kanpur), May 2005

  6. Hansen, N., Finck, S., Ros, R., Auger, A.: Real-parameter black-box optimization benchmarking 2009: noisy functions definitions. Technical Report RR-6869, INRIA (2009)

  7. Schumer, M., Steiglitz, K.: Adaptive step size random search. IEEE Trans. Autom. Control 13, 270–276 (1968)

    Article  Google Scholar 

  8. Rechenberg, I.: Evolutionstrategie: Optimierung Technisher Systeme nach Prinzipien des Biologischen Evolution. Fromman-Hozlboog Verlag, Stuttgart (1973)

    Google Scholar 

  9. Schwefel, H.-P.: Collective phenomena in evolutionary systems. In: Checkland, P., Kiss, I. (eds.) Problems of Constancy and Change—The Complementarity of Systems Approaches to Complexity. Proc. 31st Annual Meeting, vol. 2, pp. 1025–1033. Int’l Soc. for General System Research, Budapest (1987)

    Google Scholar 

  10. Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolut. Comput. 9(2), 159–195 (2001)

    Article  Google Scholar 

  11. Auger, A., Hansen, N.: Reconsidering the progress rate theory for evolution strategies in finite dimensions. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2006), pp. 445–452. Assoc. Comput. Mach., New York (2006)

    Chapter  Google Scholar 

  12. Jebalia, M., Auger, A., Liardet, P.: Log-linear convergence and optimal bounds for the (1+1)-ES. In: Monmarché, N., et al. (eds.) Proceedings of Evolution Artificielle (EA’07). LNCS, vol. 4926, pp. 207–218. Springer, Berlin (2008)

    Google Scholar 

  13. Bienvenüe, A., François, O.: Global convergence for evolution strategies in spherical problems: some simple proofs and difficulties. Theor. Comput. Sci. 306(1–3), 269–289 (2003)

    Article  MATH  Google Scholar 

  14. Auger, A.: Convergence results for (1,λ)-SA-ES using the theory of φ-irreducible Markov chains. Theor. Comput. Sci. 334(1–3), 35–69 (2005)

    Article  MATH  MathSciNet  Google Scholar 

  15. Jägersküpper, J.: Analysis of a simple evolutionary algorithm for minimization in euclidean spaces. Theor. Comput. Sci. 379(3), 329–347 (2007)

    Article  MATH  Google Scholar 

  16. Jägersküpper, J.: Rigorous runtime analysis of the (1+1)-ES: 1/5-rule and ellipsoidal fitness landscapes. In: Foundations of Genetic Algorithms: 8th International Workshop, FoGA 2005. LNCS, vol. 3469, pp. 260–281. Springer, Berlin (2005)

    Google Scholar 

  17. Arnold, D.V., Beyer, H.-G.: Efficiency and mutation strength adaptation of the (μ/μ I ,λ)-ES in a noisy environment. In: Schoenauer, M., et al. (eds.) Proceedings of Parallel Problem Solving from Nature—PPSN VI. LNCS, vol. 1917, pp. 39–48. Springer, Berlin (2000)

    Chapter  Google Scholar 

  18. Arnold, D.V., Beyer, H.-G.: Investigation of the (μ,λ)-ES in the presence of noise. In: Proceedings of 2001 IEEE Congress on Evolutionary Computation, pp. 332–339. IEEE Press, New York (2001)

    Google Scholar 

  19. Beyer, H.-G.: The Theory of Evolution Strategies. Natural Computing Series. Springer, Berlin (2001)

    Google Scholar 

  20. Arnold, D.V., Beyer, H.-G.: Local performance of the (1+1)-ES in a noisy environment. IEEE Trans. Evolut. Comput. 6(1), 30–41 (2002)

    Article  MathSciNet  Google Scholar 

  21. Jebalia, M., Auger, A.: On multiplicative noise models for stochastic search. In: Rudolph, G., Jansen, T., Lucas, S., Polini, C., Beume, N. (eds.) Proceedings of Parallel Problem Solving from Nature (PPSN X). LNCS, vol. 5199, pp. 52–61. Springer, Berlin (2008)

    Chapter  Google Scholar 

  22. Rudolph, G.: Convergence Properties of Evolutionary Algorithms. Verlag Dr. Kovac, Hamburg (1997)

    Google Scholar 

  23. Arnold, D.V.: Optimal weighted recombination. In: Foundations of Genetic Algorithms, vol. 8, pp. 215–237. Springer, Berlin (2005)

    Chapter  Google Scholar 

  24. Meyn, S.P., Tweedie, R.L.: Markov Chains and Stochastic Stability. Springer, New York (1993)

    MATH  Google Scholar 

  25. Nakama, T.: Theoretical analysis of genetic algorithms in noisy environments based on Markov model. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008), pp. 1001–1008. Assoc. Comput. Mach., New York (2008)

    Chapter  Google Scholar 

  26. Nakama, T.: Markov chain analysis of genetic algorithms in a wide variety of noisy environments. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2009), pp. 827–834. Assoc. Comput. Mach., New York (2009)

    Chapter  Google Scholar 

  27. Beyer, H.-G.: Toward a theory of evolution strategies: some asymptotical results from the (1,+λ)-theory. Evolut. Comput. 1(2), 165–188 (1993)

    Article  Google Scholar 

  28. Hansen, N., Niederberger, A., Guzzella, L., Koumoutsakos, P.: A method for handling uncertainty in evolutionary optimization with an application to feedback control of combustion. IEEE Trans. Evolut. Comput. 13(1), 180–197 (2009)

    Article  Google Scholar 

  29. Hansen, N.: Benchmarking a BI-population CMA-ES on the BBOB-2009 noisy testbed. In: Raidl, G., et al. (eds.) Workshop Proceedings of the GECCO Genetic and Evolutionary Computation Conference, pp. 2397–2402. Assoc. Comput. Mach., New York (2009)

    Google Scholar 

  30. Teytaud, O., Gelly, S.: General lower bounds for evolutionary algorithms. In: 10th International Conference on Parallel Problem Solving from Nature (PPSN 2006), vol. 4193, pp. 21–31. Springer, Berlin (2006)

    Google Scholar 

  31. Williams, D.: Probability with Martingales. Cambridge University Press, Cambridge (1991)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. TAO Team—INRIA Saclay-Île-de-France, LRI—Paris-Sud University, 91405, Orsay Cedex, France

    Mohamed Jebalia, Anne Auger & Nikolaus Hansen

Authors
  1. Mohamed Jebalia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anne Auger
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nikolaus Hansen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anne Auger.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Jebalia, M., Auger, A. & Hansen, N. Log-Linear Convergence and Divergence of the Scale-Invariant (1+1)-ES in Noisy Environments. Algorithmica 59, 425–460 (2011). https://doi.org/10.1007/s00453-010-9403-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00453-010-9403-3

Keywords

Search

Navigation