A Taxonomy of Online Stopping Criteria for Multi-Objective Evolutionary Algorithms

  • Tobias Wagner
  • Heike Trautmann
  • Luis Martí
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6576)

Abstract

The use of multi-objective evolutionary algorithms for solving black-box problems with multiple conflicting objectives has become an important research area. However, when no gradient information is available, the examination of formal convergence or optimality criteria is often impossible. Thus, sophisticated heuristic online stopping criteria (OSC) have recently become subject of intensive research. In order to establish formal guidelines for a systematic research, we present a taxonomy of OSC in this paper. We integrate the known approaches within the taxonomy and discuss them by extracting their building blocks. The formal structure of the taxonomy is used as a basis for the implementation of a comprehensive MATLAB toolbox. Both contributions, the formal taxonomy and the MATLAB implementation, provide a framework for the analysis and evaluation of existing and new OSC approaches.

Keywords

Convergence Detection Multi-Objective Optimization Performance Indicators Performance Assessment Termination Criterion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Beume, N., Naujoks, B., Emmerich, M.: SMS-EMOA: Multiobjective selection based on dominated hypervolume. European Journal of Operational Research 181(3), 1653–1669 (2007)CrossRefMATHGoogle Scholar
  2. 2.
    Beume, N., Laumanns, M., Rudolph, G.: Convergence rates of (1+1) evolutionary multiobjective optimization algorithms. In: Schaefer, R., Cotta, C., Kołodziej, J., Rudolph, G. (eds.) PPSN XI. LNCS, vol. 6238, pp. 597–606. Springer, Heidelberg (2010)Google Scholar
  3. 3.
    Bui, L.T., Wesolkowski, S., Bender, A., Abbass, H.A., Barlow, M.: A dominance-based stability measure for multi-objective evolutionary algorithms. In: Tyrrell, A., et al. (eds.) Proc. Int’l. Congress on Evolutionary Computation (CEC 2009), pp. 749–756. IEEE Press, Piscataway (2009)Google Scholar
  4. 4.
    Deb, K., Jain, S.: Running performance metrics for evolutionary multi-objective optimization. In: Simulated Evolution and Learning (SEAL), pp. 13–20 (2002)Google Scholar
  5. 5.
    Deb, K., Pratap, A., Agarwal, S.: A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans. on Evolutionary Computation 6(8) (2002)Google Scholar
  6. 6.
    Deb, K., Miettinen, K., Chaudhuri, S.: Toward an estimation of nadir objective vector using a hybrid of evolutionary and local search approaches. Trans. Evol. Comp. 14, 821–841 (2010)CrossRefGoogle Scholar
  7. 7.
    Efron, B.: Bootstrap methods: Another look at the jackknife. Annals of Statistics 7(1), 1–26 (1979)MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Goel, T., Stander, N.: A non-dominance-based online stopping criterion for multi–objective evolutionary algorithms. International Journal for Numerical Methods in Engineering (Online access) (2010) doi: 10.1002/nme.2909Google Scholar
  9. 9.
    Guerrero, J.L., Martí, L., García, J., Berlanga, A., Molina, J.M.: Introducing a robust and efficient stopping criterion for MOEAs. In: Fogel, G., Ishibuchi, H. (eds.) Proc. Int’l. Congress on Evolutionary Computation (CEC 2010), pp. 1–8. IEEE Press, Piscataway (2010)Google Scholar
  10. 10.
    Hansen, M.P., Jaszkiewicz, A.: Evaluating the quality of approximations to the non-dominated set. Tech. Rep. IMM-REP-1998-7, Institute of Mathematical Modelling, Technical University of Denmark (1998)Google Scholar
  11. 11.
    Martí, L., García, J., Berlanga, A., Molina, J.M.: A cumulative evidential stopping criterion for multiobjective optimization evolutionary algorithms. In: Thierens, D., et al. (eds.) Proc. of the 9th Annual Conference on Genetic and Evolutionary Computation (GECCO 2007), p. 911. ACM Press, New York (2007)CrossRefGoogle Scholar
  12. 12.
    Martí, L., García, J., Berlanga, A., Molina, J.M.: An approach to stopping criteria for multi-objective optimization evolutionary algorithms: The MGBM criterion. In: Tyrrell, A., et al. (eds.) Proc. Int’l. Congress on Evolutionary Computation (CEC 2009), pp. 1263–1270. IEEE Press, Piscataway (2009)Google Scholar
  13. 13.
    Mersmann, O., Trautmann, H., Naujoks, B., Weihs, C.: On the distribution of EMOA hypervolumes. In: Blum, C., Battiti, R. (eds.) LION 4. LNCS, vol. 6073, pp. 333–337. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Naujoks, B., Trautmann, H.: Online convergence detection for multiobjective aerodynamic applications. In: Tyrrell, A., et al. (eds.) Proc. Int’l. Congress on Evolutionary Computation (CEC 2009), pp. 332–339. IEEE press, Piscataway (2009)Google Scholar
  15. 15.
    Rudenko, O., Schoenauer, M.: A steady performance stopping criterion for pareto-based evolutionary algorithms. In: The 6th International Multi-Objective Programming and Goal Programming Conference, Hammamet, Tunisia (2004)Google Scholar
  16. 16.
    Trautmann, H., Wagner, T., Preuss, M., Mehnen, J.: Statistical methods for convergence detection of multiobjective evolutionary algorithms. Evolutionary Computation Journal, Special Issue: Twelve Years of EC Research in Dortmund 17(4), 493–509 (2009)CrossRefGoogle Scholar
  17. 17.
    Wagner, T., Beume, N., Naujoks, B.: Pareto-, aggregation-, and indicator-based methods in many-objective optimization. In: Obayashi, S., et al. (eds.) EMO 2007. LNCS, vol. 4403, pp. 742–756. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  18. 18.
    Wagner, T., Martí, L.: Taxonomy-based matlab framework for online stopping criteria (2010), http://www.giaa.inf.uc3m.es/miembros/lmarti/stopping
  19. 19.
    Wagner, T., Trautmann, H.: Online convergence detection for evolutionary multi-objective algorithms revisited. In: Fogel, G., Ishibuchi, H. (eds.) Proc. Int’l. Congress on Evolutionary Computation (CEC 2010), pp. 3554–3561. IEEE press, Piscataway (2010)Google Scholar
  20. 20.
    Wagner, T., Trautmann, H., Naujoks, B.: OCD: Online convergence detection for evolutionary multi-objective algorithms based on statistical testing. In: Ehrgott, M., et al. (eds.) EMO 2009. LNCS, vol. 5467, pp. 198–215. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  21. 21.
    Zitzler, E., Thiele, L., Laumanns, M., Fonseca, C., Fonseca, V.: Performance assessment of multiobjective optimizers: An analysis and review. IEEE Transactions on Evolutionary Computation 8(2), 117–132 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Tobias Wagner
    • 1
  • Heike Trautmann
    • 2
  • Luis Martí
    • 3
  1. 1.Institute of Machining Technology (ISF)TU DortmundDortmundGermany
  2. 2.Department of Computational StatisticsTU DortmundDortmundGermany
  3. 3.Group of Applied Artificial IntelligenceUniversidad Carlos III de MadridMadridSpain

Personalised recommendations