A Simplified Run Time Analysis of the Univariate Marginal Distribution Algorithm on LeadingOnes

With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LeadingOnes benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum within a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. With similar arguments as in our upper-bound analysis, we also obtain the first lower bound for this problem. Under similar assumptions, we prove that a bound that matches our upper bound up to constant factors holds with high probability.

[1]  H. Mühlenbein,et al.  From Recombination of Genes to the Estimation of Distributions I. Binary Parameters , 1996, PPSN.

[2]  Per Kristian Lehre,et al.  Improved runtime bounds for the univariate marginal distribution algorithm via anti-concentration , 2017, GECCO.

[3]  Carsten Witt,et al.  Theory of estimation-of-distribution algorithms , 2018, GECCO.

[4]  Carsten Witt,et al.  Lower Bounds on the Run Time of the Univariate Marginal Distribution Algorithm on OneMax , 2017, FOGA '17.

[5]  Duc-Cuong Dang,et al.  Level-Based Analysis of the Univariate Marginal Distribution Algorithm , 2018, Algorithmica.

[6]  Carsten Witt,et al.  Upper Bounds on the Running Time of the Univariate Marginal Distribution Algorithm on OneMax , 2018, Algorithmica.

[7]  Benjamin Doerr,et al.  The Univariate Marginal Distribution Algorithm Copes Well with Deception and Epistasis , 2020, Evolutionary Computation.

[8]  Benjamin Doerr,et al.  A tight runtime analysis for the cGA on jump functions: EDAs can cross fitness valleys at no extra cost , 2019, GECCO.

[9]  Per Kristian Lehre,et al.  Runtime analysis of the univariate marginal distribution algorithm under low selective pressure and prior noise , 2019, GECCO.

[10]  Per Kristian Lehre,et al.  On the limitations of the univariate marginal distribution algorithm to deception and where bivariate EDAs might help , 2019, FOGA '19.

[11]  Weijie Zheng,et al.  Sharp Bounds for Genetic Drift in EDAs , 2019, ArXiv.

[12]  Dirk Sudholt,et al.  Medium step sizes are harmful for the compact genetic algorithm , 2018, GECCO.

[13]  Duc-Cuong Dang,et al.  Simplified Runtime Analysis of Estimation of Distribution Algorithms , 2015, GECCO.

[14]  Weijie Zheng,et al.  Sharp Bounds for Genetic Drift in Estimation of Distribution Algorithms , 2020, IEEE Transactions on Evolutionary Computation.

[15]  J. A. Lozano,et al.  Estimation of Distribution Algorithms , 2002, Genetic Algorithms and Evolutionary Computation.

[16]  Benjamin Doerr,et al.  Probabilistic Tools for the Analysis of Randomized Optimization Heuristics , 2018, Theory of Evolutionary Computation.

[17]  Benjamin Doerr,et al.  Multiplicative Up-Drift , 2019, Algorithmica.