Critical Issues in Model-Based Surrogate Functions in Estimation of Distribution Algorithms

  • Roberto Santana
  • Alexander Mendiburu
  • Jose A. Lozano
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8298)


In many optimization domains the solution of the problem can be made more efficient by the construction of a surrogate fitness model. Estimation of distribution algorithms (EDAs) are a class of evolutionary algorithms particularly suitable for the conception of model-based surrogate techniques. Since EDAs generate probabilistic models, it is natural to use these models as surrogates. However, there exist many types of models and methods to learn them. The issues involved in the conception of model-based surrogates for EDAs are various and some of them have received scarce attention in the literature. In this position paper, we propose a unified view for model-based surrogates in EDAs and identify a number of critical issues that should be dealt with in order to advance the research in this area.


estimation of distribution algorithms surrogate functions function approximation probabilistic modeling most probable configuration abductive inference 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bielza, C., Li, G., Larranaga, P.: Multi-dimensional classification with Bayesian networks. International Journal of Approximate Reasoning 52(6), 705–727 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Bosman, P.A.: Design and Application of Iterated Density-Estimation Evolutionary Algorithms. PhD thesis, Universiteit Utrecht, Utrecht, The Netherlands (2003)Google Scholar
  3. 3.
    Bosman, P.A., Thierens, D.: Multi-objective optimization with diversity preserving mixture-based iterated density estimation evolutionary algorithms. International Journal of Approximate Reasoning 31(3), 259–289 (2002)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Brownlee, A.E.I., Regnier-Coudert, O., McCall, J.A., Massie, S., Stulajter, S.: An application of a GA with Markov network surrogate to feature selection. International Journal of Systems Science 44(11), 2039–2056 (2013)CrossRefGoogle Scholar
  5. 5.
    Brownlee, A.E.I., McCall, J., Shakya, S.K.: The Markov Network Fitness Model. In: Shakya, S., Santana, R. (eds.) Markov Networks in Evolutionary Computation, vol. 14, pp. 125–140. Springer (2012)Google Scholar
  6. 6.
    Brownlee, A.E.I., McCall, J., Zhang, Q., Brown, D.: Approaches to selection and their effect on fitness modelling in an estimation of distribution algorithm. In: Proceedings of the 2008 Congress on Evolutionary Computation, CEC 2008, Hong Kong, pp. 2621–2628. IEEE Press (2008)Google Scholar
  7. 7.
    Butz, M.V., Pelikan, M., Llorá, X., Goldberg, D.E.: Automated global structure extraction for effective local building block processing in XCS. Evolutionary Computation 14(3), 345–380 (2006)CrossRefGoogle Scholar
  8. 8.
    Campigotto, P., Passerini, A., Battiti, R.: Active learning of Pareto fronts. Technical Report DISI-13-001, University of Trento (2013)Google Scholar
  9. 9.
    Ceberio, J., Irurozki, E., Mendiburu, A., Lozano, J.A.: A review on estimation of distribution algorithms in permutation-based combinatorial optimization problems. Progress in Artificial Intelligence 1(1), 103–117 (2012)CrossRefGoogle Scholar
  10. 10.
    Ceberio, J., Mendiburu, A., Lozano, J.A.: The Plackett-Luce ranking model on permutation-based optimization problems. In: 2013 IEEE Congress on Evolutionary Computation (CEC), pp. 494–501. IEEE (2013)Google Scholar
  11. 11.
    Coello, C., Lamont, G., Van Veldhuizen, D.: Evolutionary Algorithms for Solving Multi-objective Problems. Springer-Verlag New York Inc. (2007)Google Scholar
  12. 12.
    de Waal, P.R., van der Gaag, L.C.: Inference and learning in multi-dimensional Bayesian network classifiers. In: Mellouli, K. (ed.) ECSQARU 2007. LNCS (LNAI), vol. 4724, pp. 501–511. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Deb, K., Saxena, D.K.: On finding Pareto-optimal solutions through dimensionality reduction for certain large-dimensional multi-objective optimization problems. KanGAL Report 2005011, Kanpur Genetic Algorithms Laboratory (KanGAL). Indian Institute of Technology Kanpur (2005)Google Scholar
  14. 14.
    Echegoyen, C., Mendiburu, A., Santana, R., Lozano, J.A.: Analyzing the k most probable solutions in EDAs based on Bayesian networks. In: Exploitation of Linkage Learning in Evolutionary Algorithms, Evolutionary, pp. 163–189. Springer (2010)Google Scholar
  15. 15.
    Echegoyen, C., Mendiburu, A., Santana, R., Lozano, J.A.: Toward understanding EDAs based on bayesian networks through a quantitative analysis. IEEE Transactions on Evolutionary Computation 16(2), 173–189 (2012)CrossRefGoogle Scholar
  16. 16.
    Höns, R., Santana, R., Larrañaga, P., Lozano, J.A.: Optimization by max-propagation using Kikuchi approximations. Technical Report EHU-KZAA-IK-2/07, Department of Computer Science and Artificial Intelligence, University of the Basque Country (November 2007)Google Scholar
  17. 17.
    Jin, Y.: Surrogate-assisted evolutionary computation: Recent advances and future challenges. Swarm and Evolutionary Computation 1(2), 61–70 (2011)CrossRefGoogle Scholar
  18. 18.
    Karshenas, H.: Regularized model learning in EDAs for continuous and multiobjective optimization. PhD thesis, Technical University of Madrid, Spain (2013)Google Scholar
  19. 19.
    Karshenas, H., Santana, R., Bielza, C., Larrañaga, P.: Continuous estimation of distribution algorithms based on factorized Gaussian Markov networks. In: Shakya, S., Santana, R. (eds.) Markov Networks in Evolutionary Computation, pp. 157–173. Springer (2012)Google Scholar
  20. 20.
    Karshenas, H., Santana, R., Bielza, C., Larrañaga, P.: Multi-objective optimization based on joint probabilistic modeling of objectives and variables. IEEE Transactions on Evolutionary Computation (accepted for publication, 2013)Google Scholar
  21. 21.
    Larrañaga, P., Karshenas, H., Bielza, C., Santana, R.: A review on probabilistic graphical models in evolutionary computation. Journal of Heuristics 18(5), 795–819 (2012)CrossRefGoogle Scholar
  22. 22.
    Larrañaga, P., Lozano, J.A. (eds.): Estimation of Distribution Algorithms. A New Tool for Evolutionary Computation. Kluwer Academic Publishers, Boston (2002)zbMATHGoogle Scholar
  23. 23.
    López, A., Coello, C.A., Chakraborty, D.: Objective reduction using a feature selection technique. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2008, pp. 673–680. ACM, New York (2008)CrossRefGoogle Scholar
  24. 24.
    Lozano, J.A., Larrañaga, P., Inza, I., Bengoetxea, E. (eds.): Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms. Springer (2006)Google Scholar
  25. 25.
    Marti, L., Garcia, J., Berlanga, A., Coello, C.A., Molina, J.M.: On current model-building methods for multi-objective estimation of distribution algorithms: Shortcommings and directions for improvement. Technical Report GIAA2010E001, Department of Informatics of the Universidad Carlos III de Madrid, Madrid, Spain (2010)Google Scholar
  26. 26.
    Mendiburu, A., Santana, R., Lozano, J.A.: Introducing belief propagation in estimation of distribution algorithms: A parallel framework. Technical Report EHU-KAT-IK-11/07, Department of Computer Science and Artificial Intelligence, University of the Basque Country (October 2007)Google Scholar
  27. 27.
    Miquélez, T., Bengoetxea, E., Larrañaga, P.: Evolutionary computation based on Bayesian classifiers. International Journal of Applied Mathematics and Computer Science 14(3), 101–115 (2004)Google Scholar
  28. 28.
    Mühlenbein, H., Mahnig, T.: Evolutionary algorithms: from recombination to search distributions. In: Theoretical Aspects of Evolutionary Computing, pp. 137–176. Springer, Berlin (2000)Google Scholar
  29. 29.
    Munetomo, M., Murao, N., Akama, K.: Introducing assignment functions to Bayesian optimization algorithms. Information Sciences 178(1), 152–163 (2008)CrossRefzbMATHGoogle Scholar
  30. 30.
    Oriols-Puis, Bernardó-Manilla, E., Pastry, K., Goldberg, D.E.: Substructures surrogates for learning decomposable classification problems: Implementation and first results, London, UK, pp. 2875–2882. ACE Press (2007)Google Scholar
  31. 31.
    Pelikan, M., Sastry, K., Goldberg, D.E.: Multiobjective estimation of distribution algorithms. In: Pelikan, M., Sastry, K., Cantú-Paz, E. (eds.) Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications. SCI, pp. 223–248. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  32. 32.
    Pereira, F.B., Machado, P., Costa, E., Cardoso, A., Ochoa, A., Santana, R., Soto, M.R.: Too busy to learn. In: Proceedings of the 2000 Congress on Evolutionary Computation, CEC 2000, La Jolla Marriott Hotel La Jolla, California, USA, pp. 720–727. IEEE Press (July 2000)Google Scholar
  33. 33.
    Regnier-Coudert, O.: Bayesian network structure learning using characteristic properties of permutation representations with applications to prostate cancer treatment. PhD thesis, Robert Gordon University (2013)Google Scholar
  34. 34.
    Rivera, J.P., Santana, R.: Design of an algorithm based on the estimation of distributions to generate new rules in the XCS classifier system. Technical Report ICIMAF 2000-100, CEMAFIT 2000-78, Institute of Cybernetics, Mathematics and Physics, Havana, Cuba (June 2000)Google Scholar
  35. 35.
    Santana, R.: An analysis of the performance of the mixture of trees factorized distribution algorithm when priors and adaptive learning are used. Technical Report ICIMAF 2002-180, Institute of Cybernetics, Mathematics and Physics, Havana, Cuba (March 2002)Google Scholar
  36. 36.
    Santana, R.: Factorized distribution algorithms: Selection without selected population. In: Proceedings of the 17th European Simulation Multiconference, ESM-2003, Nottingham, England, pp. 91–97 (2003)Google Scholar
  37. 37.
    Santana, R., Armañanzas, R., Bielza, C., Larrañaga, P.: Network measures for information extraction in evolutionary algorithms. International Journal of Computational Intelligence Systems 6(6), 1163–1188 (2013)CrossRefGoogle Scholar
  38. 38.
    Santana, R., Bielza, C., Larrañaga, P., Lozano, J.A., Echegoyen, C., Mendiburu, A., Armañanzas, R., Shakya, S.: Mateda-2.0: A MATLAB package for the implementation and analysis of estimation of distribution algorithms. Journal of Statistical Software 35(7), 1–30 (2010)Google Scholar
  39. 39.
    Santana, R., Karshenas, H., Bielza, C., Larrañaga, P.: Quantitative genetics in multi-objective optimization algorithms: From useful insights to effective methods. In: Proceedings of the 2011 Genetic and Evolutionary Computation Conference, GECCO 2011, Dublin, Ireland, pp. 91–92 (2011)Google Scholar
  40. 40.
    Santana, R., Shakya, S.: Probabilistic graphical models and Markov networks. In: Shakya, S., Santana, R. (eds.) Markov Networks in Evolutionary Computation, pp. 3–19. Springer (2012)Google Scholar
  41. 41.
    Sastry, K., Pelikan, M., Goldberg, D.: Efficiency enhancement of genetic algorithms via building-block-wise fitness estimation. In: Proceedings of the 2004 Congress on Evolutionary Computation, CEC 2004, Portland, Oregon, pp. 720–727. IEEE Press (2004)Google Scholar
  42. 42.
    Shakya, S., McCall, J., Brown, D.: Using a Markov network model in a univariate EDA: An empirical cost-benefit analysis. In: Beyer, H.-G., O’Reilly, U.-M. (eds.) Proceedings of Genetic and Evolutionary Computation Conference, GECCO 2005, Washington, D.C, USA, pp. 727–734. ACM Press (2005)Google Scholar
  43. 43.
    Shakya, S., Santana, R. (eds.): Markov Networks in Evolutionary Computation. Springer (2012)Google Scholar
  44. 44.
    Shi, L., Rasheed, K.: A survey of fitness approximation methods applied in evolutionary algorithm. In: Tenne, Y., Goh, C.-K. (eds.) Computational Intelligence in Expensive Optimization Problems, pp. 3–28. Springer (2010)Google Scholar
  45. 45.
    Ulrich, T., Brockhoff, D., Zitzler, E.: Pattern identification in Pareto-set approximations. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2008, pp. 737–745. ACM, New York (2008)CrossRefGoogle Scholar
  46. 46.
    Valdez-Peña, I.S., Hernández-Aguirre, A., Botello-Rionda, S.: Approximating the search distribution to the selection distribution in EDAs. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2009, pp. 461–468. ACM, New York (2009)Google Scholar
  47. 47.
    Zhang, Q., Li, H.: MOEA/D: A multiobjective evolutionary algorithm based on decomposition. IEEE Transactions on Evolutionary Computation 11(6), 712–731 (2007)CrossRefGoogle Scholar
  48. 48.
    Zhou, A., Zhang, Q., Jin, Y.: Approximating the set of Pareto-optimal solutions in both the decision and objective spaces by an estimation of distribution algorithm. IEEE Transactions on Evolutionary Computation 13(5), 1167–1189 (2009)CrossRefGoogle Scholar
  49. 49.
    Zuluaga, M., Sergent, G., Krause, A., Püschel, M.: Active learning for multi-objective optimization. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), pp. 462–470 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Roberto Santana
    • 1
  • Alexander Mendiburu
    • 1
  • Jose A. Lozano
    • 1
  1. 1.Intelligent Systems Group, Department of Computer Science and Artificial IntelligenceUniversity of the Basque Country (UPV/EHU)San SebastianSpain

Personalised recommendations