The Univariate Marginal Distribution Algorithm Copes Well with Deception and Epistasis

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.

[1]  Duc-Cuong Dang,et al.  Runtime Analysis of Non-elitist Populations: From Classical Optimisation to Partial Information , 2016, Algorithmica.

[2]  Marvin Künnemann,et al.  Optimizing linear functions with the (1+λ) evolutionary algorithm - Different asymptotic runtimes for different instances , 2015, Theor. Comput. Sci..

[3]  Thomas Jansen,et al.  On the analysis of the (1+1) evolutionary algorithm , 2002, Theor. Comput. Sci..

[4]  Frank Neumann,et al.  Optimal Fixed and Adaptive Mutation Rates for the LeadingOnes Problem , 2010, PPSN.

[5]  Per Kristian Lehre,et al.  When is an estimation of distribution algorithm better than an evolutionary algorithm? , 2009, 2009 IEEE Congress on Evolutionary Computation.

[6]  Benjamin Doerr,et al.  Bivariate estimation-of-distribution algorithms can find an exponential number of optima , 2020, GECCO.

[7]  Duc-Cuong Dang,et al.  Escaping Local Optima with Diversity Mechanisms and Crossover , 2016, GECCO.

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

[9]  Xiequan Fan,et al.  Exponential inequalities for martingales with applications , 2013, 1311.6273.

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

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

[12]  Per Kristian Lehre,et al.  Escaping Local Optima Using Crossover With Emergent Diversity , 2018, IEEE Transactions on Evolutionary Computation.

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

[14]  Benjamin Doerr,et al.  The univariate marginal distribution algorithm copes well with deception and epistasis , 2020, GECCO Companion.

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

[16]  Benjamin Doerr,et al.  Edge-based representation beats vertex-based representation in shortest path problems , 2010, GECCO '10.

[17]  Duc-Cuong Dang,et al.  Level-Based Analysis of Genetic Algorithms and Other Search Processes , 2014, bioRxiv.

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

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

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

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

[22]  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.

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

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

[25]  Benjamin Doerr,et al.  Significance-Based Estimation-of-Distribution Algorithms , 2018, IEEE Transactions on Evolutionary Computation.

[26]  Petr Posík.  Estimation of Distribution Algorithms , 2006 .

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

[28]  Andrew M. Sutton,et al.  On the runtime dynamics of the compact genetic algorithm on jump functions , 2018, GECCO.

[29]  Carsten Witt,et al.  Domino convergence: why one should hill-climb on linear functions , 2018, GECCO.

[30]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[31]  Timo Kötzing.  Concentration of First Hitting Times Under Additive Drift , 2015, Algorithmica.

[32]  Per Kristian Lehre,et al.  Fitness-levels for non-elitist populations , 2011, GECCO '11.

[33]  Benjamin Doerr.  Does comma selection help to cope with local optima? , 2020, GECCO.

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

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

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

[37]  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.