Abstract
In their recent work, Lehre and Nguyen (FOGA 2019) show that the univariate marginal distribution algorithm (UMDA) needs time exponential in the parent populations size to optimize the DeceivingLeadingBlocks (DLB) problem. They conclude from this result that univariate EDAs have difficulties with deception and epistasis.
In this work, we show that this negative finding is caused by an unfortunate choice of the parameters of the UMDA. When the population sizes are chosen large enough to prevent genetic drift, then the UMDA optimizes the DLB problem with high probability with at most \(\lambda (\frac{n}{2} + 2 e \ln n)\) fitness evaluations. Since an offspring population size \(\lambda \) of order \(n \log n\) can prevent genetic drift, the UMDA can solve the DLB problem with \(O(n^2 \log n)\) fitness evaluations. In contrast, for classic evolutionary algorithms no better run time guarantee than \(O(n^3)\) is known, so our result rather suggests that the UMDA can cope well with deception and epistatis.
Together with the result of Lehre and Nguyen, our result for the first time rigorously proves that running EDAs in the regime with genetic drift can lead to drastic performance losses.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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 2009, pp. 1470–1477 (2009). https://doi.org/10.1109/CEC.2009.4983116
Dang, D., et al.: Escaping local optima with diversity mechanisms and crossover. In: Proceedings of GECCO 2016, pp. 645–652 (2016). https://doi.org/10.1145/2908812.2908956
Dang, D., et al.: Escaping local optima using crossover with emergent diversity. IEEE Trans. Evol. Comput. 22(3), 484–497 (2018). https://doi.org/10.1109/TEVC.2017.2724201
Dang, D., Lehre, P.K.: Simplified runtime analysis of estimation of distribution algorithms. In: Proceedings of GECCO 2015, pp. 513–518 (2015). https://doi.org/10.1145/2739480.2754814
Doerr, B.: Analyzing randomized search heuristics via stochastic domination. Theor. Comput. Sci. 773, 115–137 (2019). https://doi.org/10.1016/j.tcs.2018.09.024
Doerr, B.: A tight runtime analysis for the cGA on jump functions: EDAs can cross fitness valleys at no extra cost. In: Proceedings of GECCO 2019, pp. 1488–1496 (2019). https://doi.org/10.1145/3321707.3321747
Doerr, B.: Probabilistic tools for the analysis of randomized optimization heuristics. In: Doerr, B., Neumann, F. (eds.) Theory of Evolutionary Computation. NCS, pp. 1–87. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-29414-4_1. https://arxiv.org/abs/1801.06733
Doerr, B., Krejca, M.S.: Significance-based estimation-of-distribution algorithms. In: Proceedings of GECCO 2018, pp. 1483–1490 (2018). https://doi.org/10.1145/3205455.3205553
Doerr, B., Künnemann, M.: Optimizing linear functions with the (1+\(\lambda \)) evolutionary algorithm - different asymptotic runtimes for different instances. Theor. Comput. Sci. 561, 3–23 (2015). https://doi.org/10.1016/j.tcs.2014.03.015
Doerr, B., Zheng, W.: Sharp bounds for genetic drift in EDAs. CoRR abs/1910.14389 (2019). https://arxiv.org/abs/1910.14389
Droste, S.: A rigorous analysis of the compact genetic algorithm for linear functions. Nat. Comput. 5(3), 257–283 (2006). https://doi.org/10.1007/s11047-006-9001-0
Droste, S., Jansen, T., Wegener, I.: On the analysis of the (1+1) evolutionary algorithm. Theor. Comput. Sci. 276(1–2), 51–81 (2002). https://doi.org/10.1016/S0304-3975(01)00182-7
Hasenöhrl, V., Sutton, A.M.: On the runtime dynamics of the compact genetic algorithm on jump functions. In: Proceedings of GECCO 2018, pp. 967–974 (2018). https://doi.org/10.1145/3205455.3205608
Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58(301), 13–30 (1963). https://doi.org/10.2307/2282952
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 (2017). https://doi.org/10.1145/3040718.3040724
Krejca, M.S., Witt, C.: Theory of estimation-of-distribution algorithms. In: Doerr, B., Neumann, F. (eds.) Theory of Evolutionary Computation. NCS, pp. 405–442. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-29414-4_9
Lehre, P.K., Nguyen, P.T.H.: Improved runtime bounds for the univariate marginal distribution algorithm via anti-concentration. In: Proceedings of GECCO 2017, pp. 1383–1390 (2017). https://doi.org/10.1145/3071178.3071317
Lehre, P.K., Nguyen, P.T.H.: On the limitations of the univariate marginal distribution algorithm to deception and where bivariate EDAs might help. In: Proceedings of FOGA 2019, pp. 154–168 (2019). https://doi.org/10.1145/3299904.3340316
Lengler, J., Sudholt, D., Witt, C.: Medium step sizes are harmful for the compact genetic algorithm. In: Proceedings of GECCO 2018, pp. 1499–1506 (2018). https://doi.org/10.1145/3205455.3205576
Mühlenbein, H., Paaß, G.: From recombination of genes to the estimation of distributions I. Binary parameters. In: Proceedings of PPSN 1996, pp. 178–187 (1996). https://doi.org/10.1007/3-540-61723-X_982
Pelikan, M., Hauschild, M.W., Lobo, F.G.: Estimation of distribution algorithms. In: Kacprzyk, J., Pedrycz, W. (eds.) Springer Handbook of Computational Intelligence, pp. 899–928. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-43505-2_45
Sudholt, D., Witt, C.: On the choice of the update strength in estimation-of-distribution algorithms and ant colony optimization. Algorithmica 81(4), 1450–1489 (2018). https://doi.org/10.1007/s00453-018-0480-z
Witt, C.: Domino convergence: why one should hill-climb on linear functions. In: Proceedings of GECCO 2018, pp. 1539–1546 (2018). https://doi.org/10.1145/3205455.3205581
Witt, C.: Upper bounds on the running time of the univariate marginal distribution algorithm on OneMax. Algorithmica 81(2), 632–667 (2018). https://doi.org/10.1007/s00453-018-0463-0
Zheng, W., Yang, G., Doerr, B.: Working principles of binary differential evolution. In: Proceedings of GECCO 2018, pp. 1103–1110 (2018). https://doi.org/10.1145/3205455.3205623
Acknowledgments
This work was supported by COST Action CA15140 and by a public grant as part of the Investissements d’avenir project, reference ANR-11-LABX-0056-LMH, LabEx LMH, in a joint call with Gaspard Monge Program for optimization, operations research and their interactions with data sciences.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Doerr, B., Krejca, M.S. (2020). The Univariate Marginal Distribution Algorithm Copes Well with Deception and Epistasis. In: Paquete, L., Zarges, C. (eds) Evolutionary Computation in Combinatorial Optimization. EvoCOP 2020. Lecture Notes in Computer Science(), vol 12102. Springer, Cham. https://doi.org/10.1007/978-3-030-43680-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-43680-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43679-7
Online ISBN: 978-3-030-43680-3
eBook Packages: Computer ScienceComputer Science (R0)