On the limits of effectiveness in estimation of distribution algorithms

Which problems a search algorithm can effectively solve is a fundamental issue that plays a key role in understanding and developing algorithms. In order to study the ability limit of estimation of distribution algorithms (EDAs), this paper experimentally tests three different EDA implementations on a sequence of additively decomposable functions (ADFs) with an increasing number of interactions among binary variables. The results show that the ability of EDAs to solve problems could be lost immediately when the degree of variable interaction is larger than a threshold. We argue that this phase-transition phenomenon is closely related with the computational restrictions imposed in the learning step of this type of algorithms. Moreover, we demonstrate how the use of unrestricted Bayesian networks rapidly becomes inefficient as the number of sub-functions in an ADF increases. The study conducted in this paper is useful in order to identify patterns of behavior in EDAs and, thus, improve their performances.

[1]  Qingfu Zhang,et al.  Structure learning and optimisation in a Markov-network based estimation of distribution algorithm , 2009, 2009 IEEE Congress on Evolutionary Computation.

[2]  Pedro Larrañaga,et al.  Learning Factorizations in Estimation of Distribution Algorithms Using Affinity Propagation , 2010, Evolutionary Computation.

[3]  Meng-Hiot Lim,et al.  Linkage in Evolutionary Computation , 2008, Linkage in Evolutionary Computation.

[4]  S. Baluja,et al.  Using Optimal Dependency-Trees for Combinatorial Optimization: Learning the Structure of the Search Space , 1997 .

[5]  H. Mühlenbein.  Convergence of Estimation of Distribution Algorithms for Finite Samples , 2007 .

[6]  Wray L. Buntine.  Theory Refinement on Bayesian Networks , 1991, UAI.

[7]  Qingfu Zhang,et al.  On stability of fixed points of limit models of univariate marginal distribution algorithm and factorized distribution algorithm , 2004, IEEE Transactions on Evolutionary Computation.

[8]  Pedro Larrañaga,et al.  Protein Folding in Simplified Models With Estimation of Distribution Algorithms , 2008, IEEE Transactions on Evolutionary Computation.

[9]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[10]  David E. Goldberg,et al.  Using Previous Models to Bias Structural Learning in the Hierarchical BOA , 2008, Evolutionary Computation.

[11]  Martin Pelikan,et al.  Hierarchical Bayesian optimization algorithm: toward a new generation of evolutionary algorithms , 2010, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

[12]  Jason H. Moore,et al.  Filling the gap between biology and computer science , 2008, BioData Mining.

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

[14]  María S. Pérez-Hernández,et al.  GA-EDA: A New Hybrid Cooperative Search Evolutionary Algorithm , 2006, Towards a New Evolutionary Computation.

[15]  Roberto Santana,et al.  Toward Understanding EDAs Based on Bayesian Networks Through a Quantitative Analysis , 2012, IEEE Transactions on Evolutionary Computation.

[16]  Qingfu Zhang,et al.  Analyzing limits of effectiveness in different implementations of estimation of distribution algorithms , 2011 .

[17]  Enrique F. Castillo,et al.  Expert Systems and Probabilistic Network Models , 1996, Monographs in Computer Science.

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

[19]  Pedro Larrañaga,et al.  The Impact of Exact Probabilistic Learning Algorithms in EDAs Based on Bayesian Networks , 2008, Linkage in Evolutionary Computation.

[20]  X. Jin.  Factor graphs and the Sum-Product Algorithm , 2002 .

[21]  Tian-Li Yu,et al.  Difficulty of linkage learning in estimation of distribution algorithms , 2009, GECCO.

[22]  David E. Goldberg,et al.  Hierarchical Bayesian Optimization Algorithm , 2006, Scalable Optimization via Probabilistic Modeling.

[23]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[24]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[25]  Robert Elliott Smith,et al.  The limitations of distribution sampling for linkage learning , 2007, 2007 IEEE Congress on Evolutionary Computation.

[26]  Jonathan L. Shapiro,et al.  Drift and Scaling in Estimation of Distribution Algorithms , 2005, Evolutionary Computation.

[27]  Yong Gao,et al.  Space Complexity of Estimation of Distribution Algorithms , 2005, Evolutionary Computation.

[28]  Martin Pelikan,et al.  An application of a multivariate estimation of distribution algorithm to cancer chemotherapy , 2008, GECCO '08.

[29]  Martin Pelikan,et al.  Analyzing Probabilistic Models in Hierarchical BOA , 2009, IEEE Transactions on Evolutionary Computation.

[30]  Bart Naudts,et al.  A comparison of predictive measures of problem difficulty in evolutionary algorithms , 2000, IEEE Trans. Evol. Comput..

[31]  Qingfu Zhang,et al.  An evolutionary algorithm with guided mutation for the maximum clique problem , 2005, IEEE Transactions on Evolutionary Computation.

[32]  Max Henrion,et al.  Propagating uncertainty in bayesian networks by probabilistic logic sampling , 1986, UAI.

[33]  D. Goldberg,et al.  BOA: the Bayesian optimization algorithm , 1999 .

[34]  David E. Goldberg,et al.  Model accuracy in the Bayesian optimization algorithm , 2011, Soft Comput..

[35]  Concha Bielza,et al.  A review of estimation of distribution algorithms in bioinformatics , 2008, BioData Mining.

[36]  Aurora Trinidad Ramirez Pozo,et al.  Effective Linkage Learning Using Low-Order Statistics and Clustering , 2009, IEEE Transactions on Evolutionary Computation.

[37]  Pedro Larrañaga,et al.  Estimation of Distribution Algorithms , 2002, Genetic Algorithms and Evolutionary Computation.

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

[39]  Qingfu Zhang,et al.  Combinations of estimation of distribution algorithms and other techniques , 2007, Int. J. Autom. Comput..