Theory and Practice of Cellular UMDA for Discrete Optimization

  • E. Alba
  • J. Madera
  • B. Dorronsoro
  • A. Ochoa
  • M. Soto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4193)


A new class of estimation of distribution algorithms (EDAs), known as cellular EDAs (cEDAs), has recently emerged. In these algorithms, the population is decentralized by partitioning it into many small collaborating subpopulations, arranged in a toroidal grid, and interacting only with its neighboring subpopulations. In this work, we study the simplest cEDA —the cellular univariate marginal distribution algorithm (cUMDA). In an attempt to explain its behaviour, we extend the well known takeover time analysis usually applied to other evolutionary algorithms to the field of EDAs. We also give in this work empirical arguments in favor of using the cUMDAs instead of its centralized equivalent.


Discrete Optimization Distribution Algorithm Cellular Version Parallel Genetic Algorithm Centralize Equivalent 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bäck, T., Fogel, D., Michalewicz, Z. (eds.): Handbook of Evolutionary Computation. Oxford University Press, Oxford (1997)MATHGoogle Scholar
  2. 2.
    Alba, E., Dorronsoro, B.: The exploration/exploitation tradeoff in dynamic cellular evolutionary algorithms. IEEE TEC 9(2), 126–142 (2005)Google Scholar
  3. 3.
    Mühlenbein, H., Paab, G.: From recombination of genes to the estimation of distributions I. Binary parameters. In: Ebeling, W., Rechenberg, I., Voigt, H.-M., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 178–187. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  4. 4.
    Larrañaga, P., Lozano, J.A. (eds.): Estimation of Distribution Algorithms. A New Tool for Evolutionary Computation. Kluwer Academic Publishers, Dordrecht (2002)MATHGoogle Scholar
  5. 5.
    Cantú-Paz, E.: Feature subset selection by estimation of distribution algorithms. In: GECCO, pp. 303–310. Morgan Kaufmann, San Francisco (2002)Google Scholar
  6. 6.
    Pelikan, M., Mühlenbein, H.: The bivariate marginal distribution algorithm. Advances in Soft Computing-Engineering Design and Manufacturing, 521–535 (1999)Google Scholar
  7. 7.
    Alba, E., Troya, J.: Improving flexibility and efficiency by adding parallelism to genetic algorithms. Statistics and Computing 12(2), 91–114 (2002)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Madera, J., Alba, E., Ochoa, A.: Parallel Estimation of Distribution Algorithms. In: Alba, E. (ed.) Parallel Metaheuristics: A New Class of Algorithms, pp. 203–222. John Wiley & Sons, Chichester (2005)CrossRefGoogle Scholar
  9. 9.
    Ochoa, A., Soto, M., Alba, E.: Cellular estimation of distribution algorithms (2006) (in preparation)Google Scholar
  10. 10.
    Bosman, P., Thierens, D.: Advancing continuous IDEAs with mixture distributions and factorization selection metrics. In: OBUPM, pp. 208–212 (2001)Google Scholar
  11. 11.
    Spiessens, P., Manderick, B.: A massively parallel genetic algorithm. In: Belew, R., Booker, L. (eds.) 4th ICGA, pp. 279–286. Morgan Kaufmann, San Francisco (1991)Google Scholar
  12. 12.
    Baluja, S.: Structure and performance of fine-grain parallelism in genetic search. In: Forrest, S. (ed.) 6th ICGA, pp. 155–162. Morgan Kaufmann, San Francisco (1993)Google Scholar
  13. 13.
    Mühlenbein, H., Schomish, M., Born, J.: The parallel genetic algorithm as a function optimizer. Parallel Computing 17, 619–632 (1991)MATHCrossRefGoogle Scholar
  14. 14.
    Manderick, B., Spiessens, P.: Fine-grained parallel genetic algorithm. In: 3rd ICGA, pp. 428–433 (1989)Google Scholar
  15. 15.
    Giacobini, M., Alba, E., Tomassini, M.: Selection intensity in asynchronous cellular evolutionary algorithms. In: GECCO, pp. 955–966. Springer, Heidelberg (2003)Google Scholar
  16. 16.
    Schaffer, J., Eshelman, L.: On crossover as an evolutionary viable strategy. In: 4th ICGA, pp. 61–68. Morgan Kaufmann, San Francisco (1991)Google Scholar
  17. 17.
    Mühlenbein, H., Schlierkamp-Voosen, D.: The science of breeding and its application to the breeder genetic algorithm (BGA). Evol. Comp. 1, 335–360 (1993)CrossRefGoogle Scholar
  18. 18.
    Mahnig, T., Mühlenbein, H.: Comparing the adaptive Boltzmann selection schedule SDS to truncation selection. In: CIMAF, pp. 121–128 (1999)Google Scholar
  19. 19.
    Jong, K.D., Potter, M., Spears, W.: Using problem generators to explore the effects of epistasis. In: 7th ICGA, pp. 338–345. Morgan Kaufmann, San Francisco (1997)Google Scholar
  20. 20.
    Stinson, D.R.: An Introduction to the Design and Analysis of Algorithms. The Charles Babbage Research Center, Canada (1985) (second edition, 1987)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • E. Alba
    • 1
  • J. Madera
    • 2
  • B. Dorronsoro
    • 1
  • A. Ochoa
    • 3
  • M. Soto
    • 3
  1. 1.Department of Computer ScienceUniversity of MálagaSpain
  2. 2.Department of ComputingCamagüey UniversityCuba
  3. 3.The Institute of Cybernetics, Mathematics and PhysicsLa HabanaCuba

Personalised recommendations