A Markovianity based optimisation algorithm

Several Estimation of Distribution Algorithms (EDAs) based on Markov networks have been recently proposed. The key idea behind these EDAs was to factorise the joint probability distribution of solution variables in terms of cliques in the undirected graph. As such, they made use of the global Markov property of the Markov network in one form or another. This paper presents a Markov Network based EDA that is based on the use of the local Markov property, the Markovianity, and does not directly model the joint distribution. We call it Markovianity based Optimisation Algorithm. The algorithm combines a novel method for extracting the neighbourhood structure from the mutual information between the variables, with a Gibbs sampler method to generate new points. We present an extensive empirical validation of the algorithm on problems with complex interactions, comparing its performance with other EDAs that use higher order interactions. We extend the analysis to other functions with discrete representation, where EDA results are scarce, comparing the algorithm with state of the art EDAs that use marginal product factorisations.

[1]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[2]  Siddhartha Shakya,et al.  Solving the Ising Spin Glass Problem using a Bivariate EDA based on Markov Random Fields , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[3]  David E. Goldberg,et al.  Bayesian Optimization Algorithm: From Single Level to Hierarchy , 2002 .

[4]  Siddhartha Shakya,et al.  An EDA based on local markov property and gibbs sampling , 2008, GECCO '08.

[5]  Pedro Larrañaga,et al.  Optimization by Max-Propagation Using Kikuchi Approximations , 2007 .

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

[7]  Pedro Larrañaga,et al.  Mixtures of Kikuchi Approximations , 2006, ECML.

[8]  R. Santana,et al.  The mixture of trees Factorized Distribution Algorithm , 2001 .

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

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

[11]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[12]  David E. Goldberg,et al.  Hierarchical BOA Solves Ising Spin Glasses and MAXSAT , 2003, GECCO.

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

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

[15]  Heinz Mühlenbein,et al.  A Factorized Distribution Algorithm Using Single Connected Bayesian Networks , 2000, PPSN.

[16]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[17]  Michael I. Jordan.  Graphical Models , 1998 .

[18]  D. Goldberg,et al.  A matrix approach for finding extrema: problems with modularity, hierarchy, and overlap , 2006 .

[19]  Alexander E. I. Brownlee,et al.  Multivariate Markov networks for fitness modelling in an estimation of distribution algorithm , 2009 .

[20]  William T. Freeman,et al.  Constructing free-energy approximations and generalized belief propagation algorithms , 2005, IEEE Transactions on Information Theory.

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

[22]  Stuart German,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1988 .

[23]  David Maxwell Chickering,et al.  Dependency Networks for Inference, Collaborative Filtering, and Data Visualization , 2000, J. Mach. Learn. Res..

[24]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[25]  D. E. Goldberg,et al.  Simple Genetic Algorithms and the Minimal, Deceptive Problem , 1987 .

[26]  BayesiannetworksPedro,et al.  Combinatorial optimization by learning and simulation of , 2000 .

[27]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[28]  Roberto Santana.  A Markov Network Based Factorized Distribution Algorithm for Optimization , 2003, ECML.

[29]  Hisashi Handa.  EDA-RL: estimation of distribution algorithms for reinforcement learning problems , 2009, GECCO '09.

[30]  Thilo Mahnig,et al.  Comparing the adaptive Boltzmann selection schedule SDS to truncation selection , 2007 .

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

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

[33]  J. M. Hammersley,et al.  Markov fields on finite graphs and lattices , 1971 .

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

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

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

[37]  Jose Miguel Puerta,et al.  Improved EDNA (estimation of dependency networks algorithm) using combining function with bivariate probability distributions , 2008, GECCO '08.

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

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

[40]  C. Bron,et al.  Algorithm 457: finding all cliques of an undirected graph , 1973 .

[41]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[42]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[43]  Roberto Santana,et al.  The Factorized Distribution Algorithm and The Junction Tree: A Learning Perspective , 2005 .

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

[45]  Carlos A. Coello Coello,et al.  Objective reduction using a feature selection technique , 2008, GECCO '08.

[46]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[47]  David E. Goldberg,et al.  Genetic Algorithm Design Inspired by Organizational Theory: Pilot Study of a Dependency Structure Matrix Driven Genetic Algorithm , 2003, GECCO.

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

[49]  Zoubin Ghahramani,et al.  Bayesian Learning in Undirected Graphical Models: Approximate MCMC Algorithms , 2004, UAI.

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

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

[52]  J. Davenport.  Editor , 1960 .

[53]  Martin V. Butz,et al.  Hierarchical BOA on random decomposable problems , 2006, GECCO '06.

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

[55]  Siddhartha Shakya,et al.  Optimization by estimation of distribution with DEUM framework based on Markov random fields , 2007, Int. J. Autom. Comput..

[56]  Pedro Larrañaga,et al.  Protein Folding in 2-Dimensional Lattices with Estimation of Distribution Algorithms , 2004, ISBMDA.

[57]  Heinz Mühlenbein,et al.  Schemata, Distributions and Graphical Models in Evolutionary Optimization , 1999, J. Heuristics.

[58]  John McCall,et al.  Updating the probability vector using MRF technique for a Univariate EDA , 2004 .

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

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

[61]  Martin Pelikan,et al.  Bayesian Optimization Algorithm , 2005 .

[62]  Stan Z. Li,et al.  Markov Random Field Modeling in Computer Vision , 1995, Computer Science Workbench.

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

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

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

[66]  R. Kikuchi.  A Theory of Cooperative Phenomena , 1951 .

[67]  Pedro Larrañaga,et al.  Exact Bayesian network learning in estimation of distribution algorithms , 2007, 2007 IEEE Congress on Evolutionary Computation.

[68]  Jose Miguel Puerta,et al.  EDNA: Estimation of Dependency Networks Algorithm , 2007, IWINAC.

[69]  Siddhartha Shakya,et al.  DEUM : a framework for an estimation of distribution algorithm based on Markov random fields , 2006 .

[70]  Grahame B. Smith.  Stuart Geman and Donald Geman, “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images”; , 1987 .

[71]  Siddhartha Shakya,et al.  Using a Markov network model in a univariate EDA: an empirical cost-benefit analysis , 2005, GECCO '05.

[72]  G. Harik.  Linkage Learning via Probabilistic Modeling in the ECGA , 1999 .

[73]  Gilbert Owusu,et al.  A fully multivariate DEUM algorithm , 2009, 2009 IEEE Congress on Evolutionary Computation.