Abstract
Estimation of Distribution Algorithms (EDAs) have been proposed as an extension of genetic algorithms.We assume that the function to be optimized is additively decomposed (ADF). The interaction graph of the ADF function is used to create exact or approximate factorizations of the Boltzmann distribution. Convergence of the algorithmMN-GIBBS is proven.MN-GIBBS uses a Markov network easily derived from the ADF and Gibbs sampling. We discuss different variants of Gibbs sampling. We show that a good approximation of the true distribution is not necessary, it suffices to use a factorization where the global optima have a large enough probability. This explains the success of EDAs in practical applications using Bayesian networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abbeel, P., Koller, D., Ng, A.: Learning factor graphs in polynomial time & sample complexity. Journ. Machine Learning Research 7, 1743–1780 (2006)
Alden, M.E.: MARLEDA: Effective Distribution Estimation through Random Fields. PhD thesis, University of Texas at Austin, Austin, USA (2007)
Andrieux, C., de Freitas, N., Doucet, A., Jordan, M.: An introduction to MCMC for machine learning. Machine Learning 50, 5–43 (2003)
Barahona, F.: On the computational complexity of the Ising spin glass models. J. Phys. A: Math. Gen. 15, 3241–3253 (1982)
Geman, D., Geman, S.: Stochastic relaxation, Gibbs sampling, and the restauration of images. IEEE Transaction on Pattern Recognition and Machine Intelligence 6, 721–741 (1984)
Gibbs, A.: Bounding the convergence time of the Gibbs sampler in Bayesian image restoration. Biometrika 87, 749–766 (2000)
Gilks, W.R., Richardson, S., Spiegelhalter, D.J.: Markov Chain Monte Carlo in Practice. Chapman & Hall, London (1996)
Guo, H., Hsu, W.: A survey of algorithms for real-time Bayesian network inference. In: KDD 2002/UAI 2002 Workshop on Real-Time Decision Support (2002), http://citeseer.ist.psu.edu/Guo2survey.html
Heckendorn, R.B., Wright, A.H.: Efficient linkage discovery by limited probing. Evolutionary Computation 12, 517–545 (2004)
Henrion, M.: Propagating uncertainty in Bayesian networks by Probabilistic Logic Sampling. In: Lemmar, J., Kanal, L. (eds.) Uncertainty in Artificial Intelligence, pp. 149–181. Elsevier, New York (1988)
Kearns, M., Vazirani, U.: An Introduction to Computational Learning Theory. MIT Press, Cambridge (1994)
Kschischang, F.R., Frey, B.J., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory 47(2), 498–519 (2001)
Lauritzen, S.L.: Graphical Models. Clarendon Press, Oxford (1996)
Levin, D.A., Peres, Y., Wilner, E.L.: Markov Chains and Mixing Times. American Mathematical Society, New York (2009)
MacKay, D.J.: Infomation Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)
Mahnig, T., Mühlenbein, H.: A new adaptive Boltzmann selection schedule SDS. In: Proceedings of the Congress on Evolutionary Computation 2001, pp. 121–128. IEEE (2001)
Mendiburu, A., Santan, R., Lozano, J.: Introducing belief propagation in Estimation of Distribution Algorithms: A Parallel Framework. Technical Report EHU-KAT-IK-11-07, Intelligent Systems Group (2007)
Mühlenbein, H., Höns, R.: The estimation of distributions and the minimum relative entropy principle. Evolutionary Computation 13(1), 1–27 (2005)
Mühlenbein, H., Höns, R.: The factorized distribution algorithm and the minimum relative entropy principle. In: Pelikan, M., Sastry, K., Cantu-Paz, E. (eds.) Scalable Optimization via Probabilistic Modeling. SCI, pp. 11–37. Springer, Berlin (2006)
Mühlenbein, H., Mahnig, T.: FDA - a scalable evolutionary algorithm for the optimization of additively decomposed functions. Evolutionary Computation 7(4), 353–376 (1999)
Mühlenbein, H., Mahnig, T.: Evolutionary optimization and the estimation of search distributions with applications to graph bipartitioning. Journal of Approximate Reasoning 31(3), 157–192 (2002)
Mühlenbein, H., Mahnig, T.: Evolutionary algorithms and the Boltzmann distribution. In: DeJong, K., Poli, R., Rowe, J.C. (eds.) Foundations of Genetic Algorithms 7, pp. 525–556. Morgan Kaufmann Publishers, San Francisco (2003)
Mühlenbein, H., Mahnig, T., Ochoa, A.: Schemata, distributions and graphical models in evolutionary optimization. Journal of Heuristics 5(2), 213–247 (1999)
Mühlenbein, H., Paaß, G.: From Recombination of Genes to the Estimation of Distributions I. Binary Parameters. In: Voigt, H.-M., Ebeling, W., Rechenberg, I., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 178–187. Springer, Heidelberg (1996)
Munetomo, M., Goldberg, D.: Linkage identification by non-monotonicity detection for overlapping functions. Evolutionary Computation 7, 377–398 (1999)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo (1988)
Santana, R.: A Markov Network Based Factorized Distribution Algorithm for Optimization. In: Lavrač, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 337–348. Springer, Heidelberg (2003)
Santana, R.: Estimation of distribution algorithms with Kikuchi approximations. Evolutionary Computation 13(1), 67–97 (2005)
Santana, R., Mühlenbein, H.: Blocked stochastic sampling versus Estimation of Distribution Algorithms. In: Proceedings of the Congress on Evolutionary Computation 2002, pp. 1390–1395. IEEE Press (2002)
Shakya, S.K.: DEUM: A framework for an Estimation of Distribution Algorithm based on Markov Random Fields. PhD thesis, Robert Gordon University, Aberdeen, Scotland (2006)
Wright, A.H., Pulavarty, S.S.: Estimation of distribution algorithm based on linkage discovery and factorization. In: Beyer, H.G., et al. (eds.) Proceedings of GECCO 2005, pp. 695–703. ACM Press (2005)
Yanover, C., Weiss, Y.: Finding the M most probable configurations using loopy belief propagation. In: Thrun, S., Saul, L., Schölkopf, B. (eds.) Advances in Neural Information Processing Systems 16, pp. 289–295. MIT Press, Cambridge (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Berlin Heidelberg
About this chapter
Cite this chapter
Mühlenbein, H. (2012). Convergence Theorems of Estimation of Distribution Algorithms. In: Shakya, S., Santana, R. (eds) Markov Networks in Evolutionary Computation. Adaptation, Learning, and Optimization, vol 14. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28900-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-28900-2_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28899-9
Online ISBN: 978-3-642-28900-2
eBook Packages: EngineeringEngineering (R0)