Skip to main content

The (1+1)-ES Reliably Overcomes Saddle Points

  • Conference paper
  • First Online:
Parallel Problem Solving from Nature – PPSN XVII (PPSN 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13399))

Included in the following conference series:

  • 929 Accesses

Abstract

It is known that step size adaptive evolution strategies (ES) do not converge (prematurely) to regular points of continuously differentiable objective functions. Among critical points, convergence to minima is desired, and convergence to maxima is easy to exclude. However, surprisingly little is known on whether ES can get stuck at a saddle point. In this work we establish that even the simple (1+1)-ES reliably overcomes most saddle points under quite mild regularity conditions. Our analysis is based on drift with tail bounds. It is non-standard in that we do not even aim to estimate hitting times based on drift. Rather, in our case it suffices to show that the relevant time is finite with full probability.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    It should be noted that a few interesting cases exist for zero eigenvalues (which should be improbable in practice), like the “Monkey saddle” \(f(x) = x_1^3 - 3 x_1 x_2^2\). We believe that this case can be analyzed with the same techniques as developed below, but it is outside the scope of this paper.

References

  1. Akimoto, Y.: Saddle point optimization with approximate minimization oracle. Tech. Rep. 2103.15985 (2021). arXiv.org

  2. Akimoto, Y., Auger, A., Glasmachers, T.: Drift theory in continuous search spaces: expected hitting time of the (1+1)-es with 1/5 success rule. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). ACM (2018)

    Google Scholar 

  3. Akimoto, Y., Nagata, Y., Ono, I., Kobayashi, S.: Theoretical analysis of evolutionary computation on continuously differentiable functions. In: Genetic and Evolutionary Computation Conference, pp. 1401–1408. ACM (2010)

    Google Scholar 

  4. Dauphin, Y.N., Pascanu, R., Gulcehre, C., Cho, K., Ganguli, S., Bengio, Y.: Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2933–2941 (2014)

    Google Scholar 

  5. Glasmachers, T.: Global convergence of the (1+1) evolution strategy. Evol. Comput. J. (ECJ) 28(1), 27–53 (2020)

    Article  Google Scholar 

  6. Hajek, B.: Hitting-time and occupation-time bounds implied by drift analysis with applications. Adv. Appli. Prob. 14(3), 502–525 (1982)

    Article  MathSciNet  Google Scholar 

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

    Article  Google Scholar 

  8. Kern, S., Müller, S.D., Hansen, N., Büche, D., Ocenasek, J., Koumoutsakos, P.: Learning probability distributions in continuous evolutionary algorithms-a comparative review. Nat. Comput. 3(1), 77–112 (2004)

    Article  MathSciNet  Google Scholar 

  9. Lehre, P.K., Witt, C.: General drift analysis with tail bounds. Tech. Rep. 1307.2559 (2013). arXiv.org

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tobias Glasmachers .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Glasmachers, T. (2022). The (1+1)-ES Reliably Overcomes Saddle Points. In: Rudolph, G., Kononova, A.V., Aguirre, H., Kerschke, P., Ochoa, G., Tušar, T. (eds) Parallel Problem Solving from Nature – PPSN XVII. PPSN 2022. Lecture Notes in Computer Science, vol 13399. Springer, Cham. https://doi.org/10.1007/978-3-031-14721-0_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-14721-0_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-14720-3

  • Online ISBN: 978-3-031-14721-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics