A Framework for Multi-model EDAs with Model Recombination

Estimation of Distribution Algorithms (EDAs) are evolutionary optimization methods that build models which estimate the distribution of promising regions in the search space. Conventional EDAs use only one single model at a time. One way to efficiently explore multiple areas of the search space is to use multiple models in parallel. In this paper, we present a general framework for both single- and multimodel EDAs. We propose the use of clustering to divide selected individuals into different groups, which are then utilized to build separate models. For the multi-model case, we introduce the concept of model recombination. This novel framework has great generality, encompassing the traditional Evolutionary Algorithm and the EDA as its extreme cases. We instantiate our framework in the form of a real-valued algorithm and apply this algorithm to some well-known benchmark functions. Numerical results show that both single- and multi-model EDAs have their own strengths and weaknesses, and that the multi-model EDA is able to prevent premature convergence.

[1]  David E. Goldberg,et al.  Multiobjective hBOA, clustering, and scalability , 2005, GECCO '05.

[2]  Thomas Weise,et al.  A General Framework for Multi-Model Estimation of Distribution Algorithms , 2010 .

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

[4]  Kurt Geihs,et al.  A tunable model for multi-objective, epistatic, rugged, and neutral fitness landscapes , 2008, GECCO '08.

[5]  Martin Pelikan,et al.  Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications (Studies in Computational Intelligence) , 2006 .

[6]  Pedro Larrañaga,et al.  Evolutionary computation based on Bayesian classifiers , 2004 .

[7]  Peter J. Rousseeuw,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1990 .

[8]  Thomas Weise,et al.  Global Optimization Algorithms -- Theory and Application , 2009 .

[9]  Chang Wook Ahn,et al.  Clustering-Based Probabilistic Model Fitting in Estimation of Distribution Algorithms , 2006, IEICE Trans. Inf. Syst..

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

[11]  Gerhard Widmer,et al.  Machine Learning: ECML-97 , 1997, Lecture Notes in Computer Science.

[12]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

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

[14]  Conor Ryan,et al.  On the diversity of diversity , 2007, 2007 IEEE Congress on Evolutionary Computation.

[15]  Marcus Gallagher,et al.  Real-valued Evolutionary Optimization using a Flexible Probability Density Estimator , 1999, GECCO.

[16]  Li Jinping,et al.  A Hybrid Evolutionary Algorithm Based on EDAs and Clustering Analysis , 2006, 2007 Chinese Control Conference.

[17]  Bernhard Sendhoff,et al.  Voronoi-based estimation of distribution algorithm for multi-objective optimization , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[18]  Xin Yao,et al.  Clustering and learning Gaussian distribution for continuous optimization , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[19]  David E. Goldberg,et al.  A Survey of Optimization by Building and Using Probabilistic Models , 2002, Comput. Optim. Appl..

[20]  Jürgen Schmidhuber,et al.  Probabilistic Incremental Program Evolution: Stochastic Search Through Program Space , 1997, ECML.

[21]  Hans-Paul Schwefel,et al.  Parallel Problem Solving from Nature — PPSN IV , 1996, Lecture Notes in Computer Science.

[22]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[23]  Michael Defoin-Platel,et al.  Quantum-Inspired Evolutionary Algorithm: A Multimodel EDA , 2009, IEEE Transactions on Evolutionary Computation.

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

[25]  Dirk Thierens,et al.  Advancing continuous IDEAs with mixture distributions and factorization selection metrics , 2001 .

[26]  David E. Goldberg,et al.  Genetic Algorithms, Clustering, and the Breaking of Symmetry , 2000, PPSN.

[27]  Conor Ryan,et al.  Maintaining Diversity in EDAs for Real-Valued Optimisation Problems , 2007, 2007 Frontiers in the Convergence of Bioscience and Information Technologies.