Sharp Bounds for Genetic Drift in Estimation of Distribution Algorithms

Estimation of distribution algorithms (EDAs) are a successful branch of evolutionary algorithms (EAs) that evolve a probabilistic model instead of a population. Analogous to genetic drift in EAs, EDAs also encounter the phenomenon that the random sampling in the model update can move the sampling frequencies to boundary values not justified by the fitness. This can result in a considerable performance loss. This article gives the first tight quantification of this effect for three EDAs and one ant colony optimizer, namely, for the univariate marginal distribution algorithm, the compact genetic algorithm, population-based incremental learning, and the max–min ant system with iteration-best update. Our results allow to choose the parameters of these algorithms in such a way that within a desired runtime, no sampling frequency approaches the boundary values without a clear indication from the objective function.

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

[2]  Dirk P. Kroese,et al.  Convergence properties of the cross-entropy method for discrete optimization , 2007, Oper. Res. Lett..

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

[4]  David E. Goldberg,et al.  The compact genetic algorithm , 1999, IEEE Trans. Evol. Comput..

[5]  C. McDiarmid.  Concentration , 1862, The Dental register.

[6]  Y. Svirezhev,et al.  Diffusion Models of Population Genetics , 1990 .

[7]  Paul A. Viola,et al.  MIMIC: Finding Optima by Estimating Probability Densities , 1996, NIPS.

[8]  Rich Caruana,et al.  Removing the Genetics from the Standard Genetic Algorithm , 1995, ICML.

[9]  Motoo Kimura,et al.  Diffusion models in population genetics , 1964, Journal of Applied Probability.

[10]  Shumeet Baluja,et al.  A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning , 1994 .

[11]  Kumara Sastry,et al.  Linkage Learning via Probabilistic Modeling in the Extended Compact Genetic Algorithm (ECGA) , 2006, Scalable Optimization via Probabilistic Modeling.

[12]  Stefan Droste,et al.  A rigorous analysis of the compact genetic algorithm for linear functions , 2006, Natural Computing.

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

[14]  Heinz Mühlenbein,et al.  FDA -A Scalable Evolutionary Algorithm for the Optimization of Additively Decomposed Functions , 1999, Evolutionary Computation.

[15]  Benjamin Doerr,et al.  Tight Analysis of the (1+1)-EA for the Single Source Shortest Path Problem , 2011, Evolutionary Computation.

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

[17]  Xin Yao,et al.  Drift analysis and average time complexity of evolutionary algorithms , 2001, Artif. Intell..

[18]  Tobias Friedrich,et al.  EDAs cannot be Balanced and Stable , 2016, GECCO.

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

[20]  Dirk Sudholt,et al.  On the Choice of the Update Strength in Estimation-of-Distribution Algorithms and Ant Colony Optimization , 2018, Algorithmica.

[21]  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.

[22]  Benjamin Doerr,et al.  Analyzing randomized search heuristics via stochastic domination , 2019, Theor. Comput. Sci..

[23]  M. Pelikán,et al.  The Bivariate Marginal Distribution Algorithm , 1999 .

[24]  Dirk Sudholt,et al.  A few ants are enough: ACO with iteration-best update , 2010, GECCO '10.

[25]  Heinz Mühlenbein,et al.  On the Mean Convergence Time of Evolutionary Algorithms without Selection and Mutation , 1994, PPSN.

[26]  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.

[27]  Pedro Larrañaga,et al.  The Convergence Behavior of the PBIL Algorithm: A Preliminary Approach , 2001 .