, Volume 81, Issue 2, pp 632–667 | Cite as

Upper Bounds on the Running Time of the Univariate Marginal Distribution Algorithm on OneMax

  • Carsten WittEmail author
Part of the following topical collections:
  1. Special Issue on Theory of Genetic and Evolutionary Computation


The Univariate Marginal Distribution Algorithm (UMDA) is a randomized search heuristic that builds a stochastic model of the underlying optimization problem by repeatedly sampling \(\lambda \) solutions and adjusting the model according to the best \(\mu \) samples. We present a running time analysis of the UMDA on the classical OneMax benchmark function for wide ranges of the parameters \(\mu \) and \(\lambda \). If \(\mu \ge c\log n\) for some constant \(c>0\) and \(\lambda =(1+\varTheta (1))\mu \), we obtain a general bound \(O(\mu n)\) on the expected running time. This bound crucially assumes that all marginal probabilities of the algorithm are confined to the interval \([1/n,1-1/n]\). If \(\mu \ge c' \sqrt{n}\log n\) for a constant \(c'>0\) and \(\lambda =(1+\varTheta (1))\mu \), the behavior of the algorithm changes and the bound on the expected running time becomes \(O(\mu \sqrt{n})\), which typically holds even if the borders on the marginal probabilities are omitted. The results supplement the recently derived lower bound \(\varOmega (\mu \sqrt{n}+n\log n)\) by Krejca and Witt (Proceedings of FOGA 2017, ACM Press, New York, pp 65–79, 2017) and turn out to be tight for the two very different choices \(\mu =c\log n\) and \(\mu =c'\sqrt{n}\log n\). They also improve the previously best known upper bound \(O(n\log n\log \log n)\) by Dang and Lehre (Proceedings of GECCO ’15, ACM Press, New York, pp 513–518, 2015) that was established for \(\mu =c\log n\) and \(\lambda =(1+\varTheta (1))\mu \).


Randomized search heuristics Estimation-of-distribution algorithms UMDA Running time analysis 



Financial support by the Danish Council for Independent Research (DFF-FNU 4002–00542) is gratefully acknowledged.


  1. 1.
    Baillon, J.-B., Cominetti, R., Vaisman, J.: A sharp uniform bound for the distribution of sums of Bernoulli trials. Comb. Probab. Comput. 25(3), 352–361 (2016)Google Scholar
  2. 2.
    Chen, T., Tang, K., Chen, G., Yao, X.: On the analysis of average time complexity of estimation of distribution algorithms. In: Proceedings of CEC ’07, pp. 453–460 (2007)Google Scholar
  3. 3.
    Chen, T., Lehre,P.K. , Tang, K., Yao, X.: When is an estimation of distribution algorithm better than an evolutionary algorithm? In: Proceedings of CEC ’09, pp. 1470–1477 (2009)Google Scholar
  4. 4.
    Chen, T., Tang, K., Chen, G., Yao, X.: Rigorous time complexity analysis of univariate marginal distribution algorithm with margins. In: Proceedings of CEC ’09, pp. 2157–2164 (2009)Google Scholar
  5. 5.
    Chen, T., Tang, K., Chen, G., Yao, X.: Analysis of computational time of simple estimation of distribution algorithms. IEEE Trans. Evol. Comput. 14(1), 1–22 (2010)CrossRefGoogle Scholar
  6. 6.
    Dang, D.-C., Lehre, P.K.: Simplified runtime analysis of estimation of distribution algorithms. In: Proceedings of GECCO ’15, pp. 513–518. ACM Press, New York (2015)Google Scholar
  7. 7.
    Droste, S.: A rigorous analysis of the compact genetic algorithm for linear functions. Nat. Comput. 5(3), 257–283 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Friedrich, T., Kötzing, T., Krejca, M.S., Sutton, A.M.: The benefit of recombination in noisy evolutionary search. In: Proceedings of ISAAC ’15, pp. 140–150. Springer, Berlin (2015)Google Scholar
  9. 9.
    Friedrich, T., Kötzing, T., Krejca, M.S.: EDAs cannot be balanced and stable. In: Proceedings of GECCO ’16, pp. 1139–1146. ACM Press, New York (2016)Google Scholar
  10. 10.
    Hajek, B.: Hitting-time and occupation-time bounds implied by drift analysis with applications. Adv. Appl. Probab. 14, 502–525 (1982)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Hauschild, M., Pelikan, M.: An introduction and survey of estimation of distribution algorithms. Swarm Evol. Comput. 1(3), 111–128 (2011)CrossRefGoogle Scholar
  12. 12.
    Johannsen, D.: Random combinatorial structures and randomized search heuristics. Ph.D. Thesis, Universität des Saarlandes, Germany (2010).
  13. 13.
    Kaas, R., Buhrman, J.M.: Mean, median and mode in binomial distributions. Stat. Neerl. 34, 13–18 (1980)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Krejca, M.S., Witt, C.: Lower bounds on the run time of the univariate marginal distribution algorithm on OneMax. In: Proceedings of FOGA 2017, pp. 65–79. ACM Press, New York (2017)Google Scholar
  15. 15.
    Larrañaga, P., Lozano, J.A. (eds.): Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation, Volume 2 of Genetic Algorithms and Evolutionary Computation. Springer, Berlin (2002)zbMATHGoogle Scholar
  16. 16.
    Lehre, P.K., Nguyen, P.T.H.: Improved runtime bounds for the univariate marginal distribution algorithm via anti-concentration. In: Proceedings of GECCO ’17, pp. 414–434. ACM Press, New York (2017)Google Scholar
  17. 17.
    Lehre, P.K., Witt, C.: Concentrated hitting times of randomized search heuristics with variable drift. In: Proceedings of ISAAC ’14, pp. 686–697. Springer, Berlin (2014). Full technical report at arXiv:1307.2559
  18. 18.
    McDiarmid, C.: Concentration. In: Habib, M., McDiarmid, C., Ramirez-Alfonsin, J., Reed, B. (eds.) Probabilistic Methods for Algorithmic Discrete Mathematics, pp. 195–247. Springer, Berlin (1998)CrossRefGoogle Scholar
  19. 19.
    Mitavskiy, B., Rowe, J.E., Cannings, C.: Theoretical analysis of local search strategies to optimize network communication subject to preserving the total number of links. Int. J. Intell. Comput. Cybern. 2(2), 243–284 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Mühlenbein, H., Paass, G.: From recombination of genes to the estimation of distributions I. Binary parameters. In: Proceedings of PPSN IV, pp. 178–187. Springer, Berlin (1996)Google Scholar
  21. 21.
    Neumann, F., Sudholt, D., Witt, C.: A few ants are enough: ACO with iteration-best update. In: Proceedings of GECCO ’10, pp. 63–70. ACM Press, New York (2010)Google Scholar
  22. 22.
    Oliveto, P.S., Witt, C.: Improved time complexity analysis of the simple genetic algorithm. Theor. Comput. Sci. 605, 21–41 (2015)MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Rowe, J.E., Sudholt, D.: The choice of the offspring population size in the (1, \(\lambda \)) evolutionary algorithm. Theor. Comput. Sci. 545, 20–38 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Samuels, S.M.: On the number of successes in independent trials. Ann. Math. Stat. 36(4), 1272–1278 (1965)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Sudholt, D.: A new method for lower bounds on the running time of evolutionary algorithms. IEEE Trans. Evol. Comput. 17(3), 418–435 (2013)CrossRefGoogle Scholar
  26. 26.
    Sudholt, D., Witt, C.: Update strength in EDAs and ACO: how to avoid genetic drift. In: Proceedings of GECCO ’16, pp. 61–68. ACM Press, New York (2016)Google Scholar
  27. 27.
    Witt, C.: Tight bounds on the optimization time of a randomized search heuristic on linear functions. Comb. Probab. Comput. 22(2), 294–318 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    Witt, C.: Upper bounds on the runtime of the univariate marginal distribution algorithm on OneMax. In: Proceedings of GECCO ’17, pp. 1415–1422 (2017)Google Scholar
  29. 29.
    Wu, Z., Michael, K., Möhring, R.H.: Stochastic runtime analysis of the cross-entropy algorithm. IEEE Trans. Evolut. Comput. 21(4), 616–628 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.DTU ComputeTechnical University of DenmarkKongens LyngbyDenmark

Personalised recommendations