A Genetic Algorithm Assisted by a Locally Weighted Regression Surrogate Model

  • Leonardo G. Fonseca
  • Heder S. Bernardino
  • Helio J. C. Barbosa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7333)

Abstract

In this paper we compare two strategies using locally weighted regression as a surrogate model to improve the efficiency of a real-coded generational genetic algorithm where a fixed budget of simulations is imposed. Only a fraction of the candidate solutions are evaluated exactly, allowing for more generations to evolve the population (the number of generations increases according to a user defined parameter). We test the proposed strategies on a set of benchmark optimization problems from the literature. The results show that the surrogate strategies can improve the performance of the GA depending on the user defined parameter. We suggest a threshold value to this parameter so that the locally weighted regression can be used to enhance the efficiency of genetic algorithms, when the number of calls to the expensive simulation is limited.

Keywords

Genetic Algorithm Surrogate Model Evolutionary Computation Weighted Regression Clonal Selection Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Grefenstette, J., Fitzpatrick, J.: Genetic search with approximate fitness evaluations. In: Proceedings of the International Conference on Genetic Algorithms and Their Applications, pp. 112–120 (1985)Google Scholar
  2. 2.
    Forrester, A.I., Keane, A.J.: Recent advances in surrogate-based optimization. Progress in Aerospace Sciences 45(1-3), 50–79 (2009)CrossRefGoogle Scholar
  3. 3.
    Jin, Y.: Surrogate-assisted evolutionary computation: Recent advances and future challenges. Swarm and Evolutionary Computation 1(2), 61–70 (2011)CrossRefGoogle Scholar
  4. 4.
    Ong, Y., Nair, P., Keane, A.: Evolutionary optimization of computationally expensive problems via surrogate modeling. AIAA Journal 41(4), 687–696 (2003)CrossRefGoogle Scholar
  5. 5.
    Yang, D., Flockton, S.J.: Evolutionary algorithms with a coarse-to-fine function smoothing. In: IEEE International Conference on Evolutionary Computation, vol. 2, pp. 657–662 (1995)Google Scholar
  6. 6.
    Sun, X.Y., Gong, D., Li, S.: Classification and regression-based surrogate model-assisted interactive genetic algorithm with individual’s fuzzy fitness. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, GECCO 2009, pp. 907–914. ACM, New York (2009)CrossRefGoogle Scholar
  7. 7.
    Jin, Y., Branke, J.: Evolutionary optimization in uncertain environments – a survey. IEEE Transactions on Evolutionary Computation 9(3) (2005)Google Scholar
  8. 8.
    Ferrari, S., Stengel, R.F.: Smooth function approximation using neural networks. IEEE Transactions on Neural Networks 16(1), 24–38 (2005)CrossRefGoogle Scholar
  9. 9.
    Emmerich, M., Giannakoglou, K., Naujoks, B.: Single- and multiobjective evolutionary optimization assisted by gaussian random field metamodels. Evolutionary Computation 10(4), 421–439 (2006)CrossRefGoogle Scholar
  10. 10.
    Giannakoglou, K.C.: Design of optimal aerodynamic shapes using stochastic optimization methods and computational intelligence. Progress in Aerospace Sciences 38(1), 43–76 (2002)CrossRefGoogle Scholar
  11. 11.
    Kecman, V.: Learning and soft computing: support vector machines, neural networks, and fuzzy logic models. In: Complex Adaptive Systems. MIT Press, Cambridge (2001)Google Scholar
  12. 12.
    Fonseca, L.G., Barbosa, H.J.C., Lemonge, A.C.C.: A similarity-based surrogate model for enhanced performance in genetic algorithms. OPSEARCH 46, 89–107 (2009)MathSciNetMATHCrossRefGoogle Scholar
  13. 13.
    Fonseca, L.G., Barbosa, H.J.C., Lemonge, A.C.C.: On similarity-based surrogate models for expensive single- and multi-objective evolutionary optimization. In: Computational Intelligence in Expensive Optimization Problems. Adaptation, Learning, and Optimization, vol. 2, pp. 219–248. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Noronha Jr., D.B., Martins, R.R., Jacob, B.P., de Souza, E.: Procedures for the strain based assessment of pipeline dents. International Journal of Pressure Vessels and Piping 87(5), 254–265 (2010)CrossRefGoogle Scholar
  15. 15.
    Salami, M., Hendtlass, T.: A fast evaluation strategy for evolutionary algorithms. Applied Soft Computing 2, 156–173 (2003)CrossRefGoogle Scholar
  16. 16.
    Pilato, C., Tumeo, A., Palermo, G., Ferrandi, F., Lanzi, P.L., Sciuto, D.: Improving evolutionary exploration to area-time optimization of FPGA designs. Journal of Systems Architecture 54(11), 1046–1057 (2008)CrossRefGoogle Scholar
  17. 17.
    Goel, T., Haftka, R., Shyy, W., Queipo, N.: Ensemble of surrogates. Structural and Multidisciplinary Optimization 33(3), 199–216 (2007)CrossRefGoogle Scholar
  18. 18.
    Acar, E., Rais-Rohani, M.: Ensemble of metamodels with optimized weight factors. Struct. Multidisc Optim. 37(3), 279–294 (2009)CrossRefGoogle Scholar
  19. 19.
    Lim, D., Jin, Y., Ong, Y.S., Sendhoff, B.: Generalizing surrogate-assisted evolutionary computation. IEEE Transactions on Evolutionary Computation 14(3), 329–355 (2010)CrossRefGoogle Scholar
  20. 20.
    Branke, J., Schmidt, C., Schmeck, H.: Efficient fitness estimation in noisy environment. In: Spector, L., et al. (eds.) Proceedings of Genetic and Evolutionary Computation, pp. 243–250. Morgan Kaufmann (2001)Google Scholar
  21. 21.
    Kern, S., Hansen, N., Koumoutsakos, P.: Local Meta-models for Optimization Using Evolution Strategies. In: Runarsson, T.P., Beyer, H.-G., Burke, E.K., Merelo-Guervós, J.J., Whitley, L.D., Yao, X. (eds.) PPSN 2006. LNCS, vol. 4193, pp. 939–948. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  22. 22.
    Halloran, J.P., Erdemir, A., van den Bogert, A.J.: Adaptive surrogate modeling for efficient coupling of musculoskeletal control and tissue deformation models. Journal of Biomechanical Engineering 131(1), 011014 (2009)CrossRefGoogle Scholar
  23. 23.
    Bernardino, H.S., Barbosa, H.J.C., Fonseca, L.G.: Surrogate-assisted clonal selection algorithms for expensive optimization problems. Evolutionary Intelligence 4, 81–97 (2011)CrossRefGoogle Scholar
  24. 24.
    Blanning, R.W.: The source and uses of sensivity information. Interfaces 4(4), 32–38 (1974)CrossRefGoogle Scholar
  25. 25.
    Ruppert, D., Wand, M.P.: Multivariate locally weighted least squares regression. The Annals of Statistics 22(3), 1346–1370 (1994)MathSciNetMATHCrossRefGoogle Scholar
  26. 26.
    Regis, R.G., Shoemaker, C.A.: Local function approximation in evolutionary algorithms for the optimization of costly functions. IEEE Trans. Evolutionary Computation 8(5), 490–505 (2004)CrossRefGoogle Scholar
  27. 27.
    Rasheed, K., Vattam, S., Ni, X.: Comparison of methods for using reduced models to speed up design optimization. In: Proceedings of Genetic and Evolutionary Computation Conference, pp. 1180–1187. Morgan Kaufmann, New York (2002)Google Scholar
  28. 28.
    Wanner, E.F., Guimaraes, F.G., Takahashi, R.H.C., Lowther, D.A., Ramirez, J.A.: Multiobjective memetic algorithms with quadratic approximation-based local search for expensive optimization in electromagnetics. IEEE Transactions on Magnetics 44(6), 1126–1129 (2008)CrossRefGoogle Scholar
  29. 29.
    Praveen, C., Duvigneau, R.: Low cost PSO using metamodels and inexact pre-evaluation: Application to aerodynamic shape design. Computer Methods in Applied Mechanics and Engineering 198(9-12), 1087–1096 (2009)MATHCrossRefGoogle Scholar
  30. 30.
    Diaz-Manriquez, A., Toscano-Pulido, G., Gomez-Flores, W.: On the selection of surrogate models in evolutionary optimization algorithms. In: 2011 IEEE Congress on Evolutionary Computation (CEC), pp. 2155–2162 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Leonardo G. Fonseca
    • 1
  • Heder S. Bernardino
    • 2
  • Helio J. C. Barbosa
    • 2
  1. 1.Dept. of Computational & Applied MechanicsFederal University of Juiz de ForaJuiz de ForaBrazil
  2. 2.National Laboratory for Scientific ComputingPetrópolisBrazil

Personalised recommendations