Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA

  • Martin Pelikan
  • Mark W. Hauschild
  • Pier Luca Lanzi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7491)


An automated technique has recently been proposed to transfer learning in the hierarchical Bayesian optimization algorithm (hBOA) based on distance-based statistics. The technique enables practitioners to improve hBOA efficiency by collecting statistics from probabilistic models obtained in previous hBOA runs and using the obtained statistics to bias future hBOA runs on similar problems. The purpose of this paper is threefold: (1) test the technique on several classes of NP-complete problems, including MAXSAT, spin glasses and minimum vertex cover; (2) demonstrate that the technique is effective even when previous runs were done on problems of different size; (3) provide empirical evidence that combining transfer learning with other efficiency enhancement techniques can often yield nearly multiplicative speedups.


Transfer learning inductive transfer learning from experience estimation of distribution algorithms hierarchical Bayesian optimization algorithm decomposable problems efficiency enhancement 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hauschild, M.W., Pelikan, M.: An introduction and survey of estimation of distribution algorithms. Swarm and Evolutionary Computation 1(3), 111–128 (2011)CrossRefGoogle Scholar
  2. 2.
    Larrañaga, P., Lozano, J.A. (eds.): Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation. Kluwer, Boston (2002)zbMATHGoogle Scholar
  3. 3.
    Pelikan, M., Goldberg, D.E., Lobo, F.: A survey of optimization by building and using probabilistic models. Computational Optimization and Applications 21(1), 5–20 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Pelikan, M.: Hierarchical Bayesian optimization algorithm: Toward a new generation of evolutionary algorithms. Springer (2005)Google Scholar
  5. 5.
    Hauschild, M.W., Pelikan, M., Sastry, K., Goldberg, D.E.: Using previous models to bias structural learning in the hierarchical BOA. Evolutionary Computation 20(1), 135–160 (2012)CrossRefGoogle Scholar
  6. 6.
    Mühlenbein, H., Mahnig, T., Rodriguez, A.O.: Schemata, distributions and graphical models in evolutionary optimization. Journal of Heuristics 5, 215–247 (1999)zbMATHCrossRefGoogle Scholar
  7. 7.
    Mühlenbein, H., Mahnig, T.: Evolutionary optimization and the estimation of search distributions with applications to graph bipartitioning. International Journal of Approximate Reasoning 31(3), 157–192 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    Baluja, S.: Incorporating a priori knowledge in probabilistic-model based optimization. In: Pelikan, Sastry, Cantú-Paz (eds.) Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications, pp. 205–219. Springer (2006)Google Scholar
  9. 9.
    Schwarz, J., Ocenasek, J.: A problem-knowledge based evolutionary algorithm KBOA for hypergraph partitioning. In: Proc. of the Fourth Joint Conf. on Knowledge-Based Software Engineering, Brno, Czech Rep., pp. 51–58 (2000)Google Scholar
  10. 10.
    Hauschild, M.W., Pelikan, M., Sastry, K., Lima, C.F.: Analyzing probabilistic models in hierarchical BOA. IEEE Transactions on Evolutionary Computation 13(6), 1199–1217 (2009)CrossRefGoogle Scholar
  11. 11.
    Pelikan, M., Hauschild, M.: Distance-based bias in model-directed optimization of additively decomposable problems. MEDAL Report No. 2012001, Missouri Estimation of Distribution Algorithms Laboratory, University of Missouri–St. Louis, St. Louis, MO (2012)Google Scholar
  12. 12.
    Pelikan, M., Sastry, K., Goldberg, D.E.: Sporadic model building for efficiency enhancement of the hierarchical BOA. Genetic Programming and Evolvable Machines 9(1), 53–84 (2008)CrossRefGoogle Scholar
  13. 13.
    Pelikan, M., Goldberg, D.E.: Escaping hierarchical traps with competent genetic algorithms. In: Genetic and Evol. Comp. Conf (GECCO 2001), pp. 511–518 (2001)Google Scholar
  14. 14.
    Chickering, D.M., Heckerman, D., Meek, C.: A Bayesian approach to learning Bayesian networks with local structure. Technical Report MSR-TR-97-07, Microsoft Research, Redmond, WA (1997)Google Scholar
  15. 15.
    Harik, G.R.: Finding multimodal solutions using restricted tournament selection. In: Proc. of the Int. Conf. on Genetic Algorithms (ICGA 1995), pp. 24–31 (1995)Google Scholar
  16. 16.
    Friedman, N., Goldszmidt, M.: Learning Bayesian networks with local structure. In: Jordan, M.I. (ed.) Graphical Models, pp. 421–459. MIT Press (1999)Google Scholar
  17. 17.
    Cooper, G.F., Herskovits, E.H.: A Bayesian method for the induction of probabilistic networks from data. Machine Learning 9, 309–347 (1992)zbMATHGoogle Scholar
  18. 18.
    Lima, C.F., Lobo, F.G., Pelikan, M., Goldberg, D.E.: Model accuracy in the Bayesian optimization algorithm. Soft Computing 15(7), 1351–1371 (2011)CrossRefGoogle Scholar
  19. 19.
    Hauschild, M., Pelikan, M.: Enhancing Efficiency of Hierarchical BOA Via Distance-Based Model Restrictions. In: Rudolph, G., Jansen, T., Lucas, S., Poloni, C., Beume, N. (eds.) PPSN X. LNCS, vol. 5199, pp. 417–427. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  20. 20.
    Hauschild, M.W., Pelikan, M.: Intelligent bias of network structures in the hierarchical BOA. In: Genetic and Evol. Comp. Conf. (GECCO 2009), pp. 413–420 (2009)Google Scholar
  21. 21.
    Pratt, L.Y., Mostow, J., Kamm, C.A., Kamm, A.A.: Direct transfer of learned information among neural networks. In: Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 584–589 (1991)Google Scholar
  22. 22.
    Caruana, R.: Multitask learning. Machine Learning 28, 41–75 (1997)CrossRefGoogle Scholar
  23. 23.
    Pelikan, M., Hartmann, A.K.: Searching for ground states of Ising spin glasses with hierarchical BOA and cluster exact approximation. In: Pelikan, M., Sastry, K., Cantú-Paz, E. (eds.) Scalable Optimization via Probabilistic Modeling: From Algorithms to Applications. Springer (2006)Google Scholar
  24. 24.
    Young, A. (ed.): Spin glasses and random fields. World Scientific, Singapore (1998)Google Scholar
  25. 25.
    Pelikan, M., Kalapala, R., Hartmann, A.K.: Hybrid evolutionary algorithms on minimum vertex cover for random graphs. In: Genetic and Evol. Comp. Conf. (GECCO 2007), pp. 547–554 (2007)Google Scholar
  26. 26.
    Weigt, M., Hartmann, A.K.: Minimal vertex covers on finite-connectivity random graphs: A hard-sphere lattice-gas picture. Physical Review E 63, 056127 (2001)Google Scholar
  27. 27.
    Pelikan, M., Goldberg, D.E.: Hierarchical BOA Solves Ising Spin Glasses and Maxsat. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2724, pp. 1271–1282. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  28. 28.
    Gent, I., Hoos, H.H., Prosser, P., Walsh, T.: Morphing: Combining structure and randomness. In: Proc. of the American Association of Artificial Intelligence (AAAI 1999), pp. 654–660 (1999)Google Scholar
  29. 29.
    Sastry, K.: Evaluation-relaxation schemes for genetic and evolutionary algorithms. Master’s thesis, University of Illinois at Urbana-Champaign, Department of General Engineering, Urbana, IL (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Martin Pelikan
    • 1
  • Mark W. Hauschild
    • 1
  • Pier Luca Lanzi
    • 2
  1. 1.Missouri Estimation of Distribution Algorithms Laboratory (MEDAL), Department of Mathematics and Computer ScienceUniversity of MissouriSt. LouisUSA
  2. 2.Dipartimento di Elettronica e InformazionePolitecnico di MilanoMilanoItaly

Personalised recommendations