A Review on Parallel Estimation of Distribution Algorithms

Estimation of Distribution Algorithms (EDAs) are a set of techniques that belong to the field of Evolutionary Computation. They are similar to Genetic Algorithms (GAs), in the sense that, given a problem, they use a population of individuals to represent solutions, and this population is made to evolve towards the most promising solutions. However, instead of using the usual GA-operators such as mutation or crossover, EDAs learn a probabilistic model that tries to capture the main characteristics of the problem. Based on this idea, several EDAs have been introduced in the last years, showing a good performance and being able to solve problems of different complexity. One important drawback of EDAs is the significant computational effort required by the utilization of probabilistic models, when applied to real-world problems. This fact has led the research community to apply parallel schemes to EDAs, as a viable way to reduce execution times. Schemes already proposed for GAs have been used as the foundation for these parallel schemes. In this chapter, we make a review of parallel EDAs, with a main focus: identifying those parts that are susceptible of parallelization. Then we describe a collection of parallelization strategies proposed in the literature. Additionally, we provide some recommendations for those that are considering the implementation of parallel EDAs on state-of-the-art parallel computers.

[1]  Message P Forum,et al.  MPI: A Message-Passing Interface Standard , 1994 .

[2]  Jose Miguel Puerta,et al.  Initial approaches to the application of islands-based parallel EDAs in continuous domains , 2005, 2005 International Conference on Parallel Processing Workshops (ICPPW'05).

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

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

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

[6]  Peter A. N. Bosman,et al.  Design and Application of iterated Density-Estimation Evolutionary Algorithms , 2003 .

[7]  Michèle Sebag,et al.  Extending Population-Based Incremental Learning to Continuous Search Spaces , 1998, PPSN.

[8]  Xavier Llorà,et al.  Towards billion-bit optimization via a parallel estimation of distribution algorithm , 2007, GECCO '07.

[9]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[10]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[11]  Enrique Alba,et al.  An Analysis of Synchronous and Asynchronous Parallel Distributed Genetic Algorithms with Structured and Panmictic Islands , 1999, IPPS/SPDP Workshops.

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

[13]  Tomoyuki Hiroyasu,et al.  Comparison of pulling back and penalty methods for constraints in DPMBGA , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[14]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

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

[16]  Jiri Ocenasek,et al.  Migration of probabilistic models for island-based bivariate EDA algorithm , 2007, GECCO '07.

[17]  Pedro Larrañaga,et al.  Parallel Estimation of Distribution Algorithms , 2002, Estimation of Distribution Algorithms.

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

[19]  Erick Cantú-Paz,et al.  Efficient and Accurate Parallel Genetic Algorithms , 2000, Genetic Algorithms and Evolutionary Computation.

[20]  Jose Miguel Puerta,et al.  Improving model combination through local search in parallel univariate EDAs , 2005, 2005 IEEE Congress on Evolutionary Computation.

[21]  P. Bosman,et al.  IDEAs based on the normal kernels probability density function , 2000 .

[22]  Alberto Ochoa,et al.  A Parallel Island Model for Estimation of Distribution Algorithms , 2006, Towards a New Evolutionary Computation.

[23]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[24]  A. A. Zhigli︠a︡vskiĭ,et al.  Theory of Global Random Search , 1991 .

[25]  John J. Grefenstette,et al.  Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[26]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[27]  Larry J. Eshelman,et al.  On Crossover as an Evolutionarily Viable Strategy , 1991, ICGA.

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

[29]  David E. Goldberg,et al.  Hierarchical Problem Solving and the Bayesian Optimization Algorithm , 2000, GECCO.

[30]  Martin Pelikan,et al.  Design of Multithreaded Estimation of Distribution Algorithms , 2003, GECCO.

[31]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .

[32]  Roberto Santana,et al.  Estimation of Distribution Algorithms with Kikuchi Approximations , 2005, Evolutionary Computation.

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

[34]  Enrique Alba,et al.  Parallel Metaheuristics: A New Class of Algorithms , 2005 .

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

[36]  Tomoyuki Hiroyasu,et al.  Distributed Probabilistic Model-Building Genetic Algorithm , 2003, GECCO.

[37]  David R. Butenhof.  Programming with POSIX threads , 1993 .

[38]  Ronald A. Howard,et al.  Influence Diagrams , 2005, Decis. Anal..

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

[40]  Pedro Larrañaga,et al.  Combinatonal Optimization by Learning and Simulation of Bayesian Networks , 2000, UAI.

[41]  Jirí Jaros,et al.  Parallel BMDA with probability model migration , 2007, 2007 IEEE Congress on Evolutionary Computation.

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

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

[44]  Pedro Larrañaga,et al.  Optimization in Continuous Domains by Learning and Simulation of Gaussian Networks , 2000 .

[45]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[46]  P. Bosman,et al.  An algorithmic framework for density estimation based evolutionary algorithms , 1999 .

[47]  J. A. Lozano,et al.  Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms (Studies in Fuzziness and Soft Computing) , 2006 .

[48]  David E. Goldberg,et al.  Multiple-Deme Parallel Estimation of Distribution Algorithms: Basic Framework and Application , 2003, PPAM.

[49]  Barbara Chapman,et al.  Using OpenMP: Portable Shared Memory Parallel Programming (Scientific and Engineering Computation) , 2007 .

[50]  Jose Miguel Puerta,et al.  Migration of Probability Models Instead of Individuals: An Alternative When Applying the Island Model to EDAs , 2004, PPSN.

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

[52]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

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

[54]  Gilbert Syswerda,et al.  Simulated Crossover in Genetic Algorithms , 1992, FOGA.

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

[56]  Heinz Mühlenbein,et al.  The Equation for Response to Selection and Its Use for Prediction , 1997, Evolutionary Computation.

[57]  Martin Pelikan,et al.  Order or not: does parallelization of model building in hBOA affect its scalability? , 2007, GECCO '07.

[58]  Alexander Mendiburu,et al.  Parallel implementation of EDAs based on probabilistic graphical models , 2005, IEEE Transactions on Evolutionary Computation.

[59]  C. Robert Kenley,et al.  Gaussian influence diagrams , 1989 .

[60]  Jiri Ocenasek,et al.  Parallel Estimation of Distribution Algorithms , 2010 .

[61]  Enrique Alba,et al.  Numerical and real time analysis of parallel distributed GAs with structured and panmictic populations , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[62]  Pedro Larrañaga,et al.  Towards a New Evolutionary Computation - Advances in the Estimation of Distribution Algorithms , 2006, Towards a New Evolutionary Computation.

[63]  Josef Schwarz,et al.  Estimation Distribution Algorithm for mixed continuous-discrete optimization problems , 2002 .

[64]  L. Darrell Whitley,et al.  Island Model genetic Algorithms and Linearly Separable Problems , 1997, Evolutionary Computing, AISB Workshop.

[65]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[66]  Enrique Alba,et al.  Parallelism and evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

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

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

[69]  W Bossert,et al.  Mathematical optimization: are there abstract limits on natural selection? , 1967, The Wistar Institute symposium monograph.

[70]  Martin Pelikan,et al.  Scalable Optimization via Probabilistic Modeling , 2006, Studies in Computational Intelligence.