Skip to main content
SpringerLink
Log in

A Factorized Distribution Algorithm Using Single Connected Bayesian Networks

  • Conference paper
Parallel Problem Solving from Nature PPSN VI (PPSN 2000)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1917))

Included in the following conference series:

Abstract

Single connected Factorized Distribution Algorithms (FDA-SC) use factorizations of the joint distribution, which are trees, forests or polytrees. At each stage of the evolution they build a polytree from which new points are sampled. We study empirically the relation between the accuracy of the learned model and the quality of the new search points generated. We show that a change of the learned model before sampling might reduce the population size requirements of sampling.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. S. Acid, L. M. de Campos. (1995). Approximations of causal networks by polytrees: an empirical study. Advances in Intelligent Computing. 149–158. B. Bouchon-Meunier, R. R. Yager, L. A. Zadeh. Lecture Notes in Computer Science 945. Springer Verlag, Berlin.

    Chapter  Google Scholar 

  2. S. Baluja and S. Davies. (1997). Using Optimal Dependency-Trees for Combinatorial Optimization: Learning the structure of the Search Space, (Carnegie Mellon Report, CMU-CS-97-107, 1997a).

    Google Scholar 

  3. C. K. Chow, C. N. Liu. (1968). Approximating discrete probability distribution with dependence trees. IEEE Transantions on Information Theory 14. 462–467.

    Article  MATH  Google Scholar 

  4. L. M. de Campos. (1998). Independency relationships and learning algorithms for singly connected networks. Journal of Experimental and Theoretical Ar-tifiacial Intelligence. 511–549. (Also DECSAI-TR-960204).

    Google Scholar 

  5. J.S. De Bonet, C. L. Isbell, and P. Viola. (1997) MIMIC: Finding Optima by Estimating Probability Densities, in M. Jordan and Th. Petsche, eds, Advances in Neural Information Processing Systems, Vol. 9. 424–431.

    Google Scholar 

  6. R. Etxeberria, P. Larranaga. (1999). Global optimization using Bayesian networks. CIMAF 1999, Second International Symposium on Artificial Intelligence, Adaptive Systems. 332–339.

    Google Scholar 

  7. I. J. Good. (1965). The estimation of probabilities. MIT Press.

    Google Scholar 

  8. M. Henrion. (1988). Propagating uncertainty in Bayesian networks by probabilistic logic sampling. Uncertainty in Artificial Intelligence 2. 317–324.

    Google Scholar 

  9. H. Muehlenbein. (1997). The equation for response to selection and its use for prediction. Evolutionary Computation 5. 303–346.

    Google Scholar 

  10. H. Muehlenbein, G. Pass. (1996). From recombination of genes to estimation of distribution I. Binay parameters. Lecture Notes in Computer Science 1411. Parallel Problem Solving from Nature-PPSN IV. 178–187.

    Chapter  Google Scholar 

  11. H. Muehlenbein, T. Mahnig, A. Ochoa. (1999). Schemata, distributions and graphical models in evolutionay optimization. Journal of Heuristics 5(2). 215–247.

    Article  MATH  Google Scholar 

  12. H. Muehlenbein, T. Mahnig. (1999). FDA: A scalable evolutionary algorithm for the optimization of additively decomposed functions. Evolutionary Computation 7(4). 353–376.

    Google Scholar 

  13. H. Muehlenbein, Th. Mahnig. (2000). Evolutionary Algorithms: From Recombination to Search Distributions. in: Theoretical Aspects of Evolutionary Computing. eds. L. Kallel, B. Naudts, A. Rogers, 137–176. Springer Verlag Berlin.

    Google Scholar 

  14. A. Ochoa, M. Soto, R. Santana, J. C. Madera, N. Jorge. (1999). The factorized distribution algorithm and the junction tree: a learning perspective. CIMAF 1999, Second International Symposium on Artificial Intelligence, Adaptive Systems. 368–377.

    Google Scholar 

  15. J. Pearl. (1988). Probabilistic reasoning in intelligent systems: networks of plausible inference. Ronald J. Brachman (AT&T Bell Laboratories). Morgan and Kaufmann.

    Google Scholar 

  16. M. Pelican, H. Muehlenbein. (1999). BMDA: The Bivariate Marginal Distribution Algorithm, in R. Roy, T. Furuhashi, P, K. Chandhory eds., Advances in Soft Computing-Engineering Design and Manufacturing, (1999), London: Springer Verlag, 521–535.

    Google Scholar 

  17. M. Pelican, D. E. Goldberg, E. Cantu-Paz. (1999). BOA: The Bayesian optimization algorithm. Proceedings of the Genetic and Evolutionary Computation Conference GECCO-99 1. 525–532.

    Google Scholar 

  18. M. Soto, A. Ochoa, S. Acid, L. M. de Campos.(1999). Introducing the poly-tree aproximation distribution algorithm. CIMAF 1999, Second International Symposium on Artificial Intelligence, Adaptive Systems. 360–367.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Real World Computing Partnership Theoretical Foundation GMD Laboratory, GMD-Forschungszentrum Informationstechnik, 53754, St. Augustin, Germany

    Alberto Ochoa & Heinz Muehlenbein

  2. Institute of Cybernetics, Mathematics and Physics Center of Mathematics and Theoretical Physics, ICIMAF, CP 10400, La Habana, Cuba

    Alberto Ochoa & Marta Soto

Authors
  1. Alberto Ochoa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Heinz Muehlenbein
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marta Soto
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. CMAP, Ecole Polytechnique, 91128, Palaiseau Cedex, France

    Marc Schoenauer

  2. Dept. of Mechanical Engineering Kanpur Genetic Algorithms Laboratory, Indian Institute of Technology Kanpur, Kanpur, Pin, 208 016, India

    Kalyanmoy Deb

  3. Fachbereich Informatik, Lehrstuhl für Systemanalyse, Universität Dortmund, Joseph-von-Fraunhofer-Str. 20, 44221, Dortmund, Germany

    Günther Rudolph  & Hans-Paul Schwefel  & 

  4. School of Computer Science, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK

    Xin Yao

  5. Projet Fractales, INRIA Rocquencourt, BP 105, 78153, Le Chesnay Cedex, France

    Evelyne Lutton

  6. Dept. de Arquitectura y Technologa de los Computadores, GeNeura Team, Universidad de Granada, Campus Fuenetenueva, s/n, Granada

    Juan Julian Merelo

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ochoa, A., Muehlenbein, H., Soto, M. (2000). A Factorized Distribution Algorithm Using Single Connected Bayesian Networks. In: Schoenauer, M., et al. Parallel Problem Solving from Nature PPSN VI. PPSN 2000. Lecture Notes in Computer Science, vol 1917. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45356-3_77

Download citation

  • DOI: https://doi.org/10.1007/3-540-45356-3_77

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-41056-0

  • Online ISBN: 978-3-540-45356-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation