When is an estimation of distribution algorithm better than an evolutionary algorithm?

Despite the wide-spread popularity of estimation of distribution algorithms (EDAs), there has been no theoretical proof that there exist optimisation problems where EDAs perform significantly better than traditional evolutionary algorithms. Here, it is proved rigorously that on a problem called SUBSTRING, a simple EDA called univariate marginal distribution algorithm (UMDA) is efficient, whereas the (1+1) EA is highly inefficient. Such studies are essential in gaining insight into fundamental research issues, i.e., what problem characteristics make an EDA or EA efficient, under what conditions an EDA is expected to outperform an EA, and what key factors are in an EDA that make it efficient or inefficient.

[1]  Xin Yao,et al.  From an individual to a population: an analysis of the first hitting time of population-based evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

[2]  Xin Yao,et al.  Time complexity of evolutionary algorithms for combinatorial optimization: A decade of results , 2007, Int. J. Autom. Comput..

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

[4]  Xin Yao,et al.  On the analysis of average time complexity of estimation of distribution algorithms , 2007, 2007 IEEE Congress on Evolutionary Computation.

[5]  Xin Yao,et al.  Rigorous time complexity analysis of Univariate Marginal Distribution Algorithm with margins , 2009, 2009 IEEE Congress on Evolutionary Computation.

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

[7]  Pietro Simone Oliveto,et al.  Analysis of population-based evolutionary algorithms for the vertex cover problem , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[8]  David E. Goldberg,et al.  Scalability of the Bayesian optimization algorithm , 2002, Int. J. Approx. Reason..

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

[10]  Xin Yao,et al.  A New Approach for Analyzing Average Time Complexity of Population-Based Evolutionary Algorithms on Unimodal Problems , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[12]  Rajeev Motwani,et al.  Randomized Algorithms , 1995, SIGA.

[13]  R. Serfling.  Probability Inequalities for the Sum in Sampling without Replacement , 1974 .

[14]  Xin Yao,et al.  A comparative study of three evolutionary algorithms incorporating different amounts of domain knowledge for node covering problem , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[15]  The Centre of Excellence for Research in Computational Intelligence and Applications , .

[16]  María Cristina González Morgado.  Contributions on theoretical aspects of estimation of distributions algorithms , 2006 .

[17]  Xin Yao,et al.  Analysis of Computational Time of Simple Estimation of Distribution Algorithms , 2010, IEEE Transactions on Evolutionary Computation.

[18]  Xin Yao,et al.  A study of drift analysis for estimating computation time of evolutionary algorithms , 2004, Natural Computing.

[19]  Pietro Simone Oliveto,et al.  Simplified Drift Analysis for Proving Lower Bounds in Evolutionary Computation , 2008, Algorithmica.

[20]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .

[21]  Xin Yao,et al.  Estimation of distribution algorithms for testing object oriented software , 2007, 2007 IEEE Congress on Evolutionary Computation.

[22]  Pietro Simone Oliveto,et al.  Evolutionary algorithms and the Vertex Cover problem , 2007, 2007 IEEE Congress on Evolutionary Computation.