Evolution Under Strong Noise: A Self-Adaptive Evolution Strategy Can Reach the Lower Performance Bound - The pcCMSA-ES

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9921)

Abstract

According to a theorem by Astete-Morales, Cauwet, and Teytaud, “simple Evolution Strategies (ES)” that optimize quadratic functions disturbed by additive Gaussian noise of constant variance can only reach a simple regret log-log convergence slope \(\ge -1/2\) (lower bound). In this paper a population size controlled ES is presented that is able to perform better than the \(-1/2\) limit. It is shown experimentally that the pcCMSA-ES is able to reach a slope of \(-1\) being the theoretical lower bound of all comparison-based direct search algorithms.

Keywords

Noise Strength Strong Noise Evolution Strategy Covariance Matrix Adaptation Significant Negative Trend 
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.

Notes

Acknowledgements

This work was supported by the Austrian Science Fund FWF under grant P22649-N23 and by the Austrian funding program COMET (COMpetence centers for Excellent Technologies) in the K-Project Advanced Engineering Design Automation (AEDA).

References

  1. 1.
    Arnold, D.V.: Noisy Optimization with Evolution Strategies. Kluwer, Amsterdam (2002)CrossRefMATHGoogle Scholar
  2. 2.
    Jin, Y., Branke, J.: Evolutionary optimization in uncertain environments - a survey. IEEE Trans. Evolut. Comput. 9(3), 303–317 (2005)CrossRefGoogle Scholar
  3. 3.
    Beyer, H.-G., Arnold, D.V., Meyer-Nieberg, S.: A new approach for predicting the final outcome of evolution strategy optimization under noise. Genet. Progr. Evol. Mach. 6(1), 7–24 (2005)CrossRefGoogle Scholar
  4. 4.
    Beyer, H.-G., Sendhoff, B.: Evolution strategies for robust optimization. In: 2006 IEEE Congress on Evolutionary Computation CEC 2006, pp. 1346–1353 (2006)Google Scholar
  5. 5.
    Hansen, N., Niederberger, A.S.P., 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)CrossRefGoogle Scholar
  6. 6.
    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)CrossRefGoogle Scholar
  7. 7.
    Astete-Morales, S., Cauwet, M.-L., Teytaud, O.: Evolution strategies with additive noise: a convergence rate lower bound. In: Proceedings of the 2015 ACM Conference on Foundations of Genetic Algorithms XIII, FOGA 2015, pp. 76–84. ACM, New York (2015)Google Scholar
  8. 8.
    Shamir, O.: On the complexity of bandit and derivative-free stochastic convex optimization. In: COLT 2013 - The 26th Annual Conference on Learning Theory, NJ, USA, pp. 3–24 (2013)Google Scholar
  9. 9.
    Kenney, J.F.: Mathematics of Statistics: Parts 1–2. Literary Licensing, LLC, New York (2013)Google Scholar
  10. 10.
    Beyer, H.-G., Melkozerov, A.: The dynamics of self-adaptive multi-recombinant evolution strategies on the general ellipsoid model. IEEE Trans. Evolut. Comput. 18(5), 764–778 (2014)CrossRefGoogle Scholar
  11. 11.
    Beyer, H.-G.: The Theory of Evolution Strategies. Natural Computing Series. Springer, Heidelberg (2001)CrossRefMATHGoogle Scholar
  12. 12.
    Melkozerov, A., Beyer, H.-G.: Towards an analysis of self-adaptive evolution strategies on the noisy ellipsoid model: progress rate and self-adaptation response. In: GECCO 2015, Madrid, Spain, pp. 297–304. ACM (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Vorarlberg University of Applied Sciences, Research Center PPEDornbirnAustria

Personalised recommendations