Local Selection of Model Parameters in Probability Density Function Estimation

  • Ezequiel López-Rubio
  • Juan Miguel Ortiz-de-Lazcano-Lobato
  • Domingo López-Rodríguez
  • Enrique Mérida-Casermeiro
  • María del Carmen Vargas-González
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)


Here we present a novel probability density estimation model. The classical Parzen window approach builds a spherical Gaussian density around every input sample. Our proposal selects a Gaussian specifically tuned for each sample, with an automated estimation of the local intrinsic dimensionality of the embedded manifold and the local noise variance. This leads to outperform other proposals where local parameter selection is not allowed, like the manifold Parzen windows.


Principal Direction Noise Variance Local Selection Finite Mixture Model Qualitative Parameter 
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.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  2. 2.
    Silverman, B.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, New York (1986)MATHGoogle Scholar
  3. 3.
    Vapnik, V.N.: Statistical Learning Theory. John Wiley & Sons, New York (1998)MATHGoogle Scholar
  4. 4.
    Izenman, A.J.: Recent developments in nonparametric density estimation. Journal of the American Statistical Association 86(413), 205–224 (1991)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Lejeune, M., Sarda, P.: Smooth estimators of distribution and density functions. Computational Statistics & Data Analysis 14, 457–471 (1992)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Hjort, N.L., Jones, M.C.: Locally Parametric Nonparametric Density Estimation. Annals of Statistics 24(4), 1619–1647 (1996)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Hastie, T., Loader, C.: Local regression: Automatic kernel carpentry. Statistical Science 8, 120–143 (1993)CrossRefGoogle Scholar
  8. 8.
    McLachlan, G., Peel, D.: Finite Mixture Models. Wiley, Chichester (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Parzen, E.: On the Estimation of a Probability Density Function and Mode. Annals of Mathematical Statistics 33, 1065–1076 (1962)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Vincent, P., Bengio, Y.: Manifold Parzen Windows. Advances in Neural Information Processing Systems 15, 825–832 (2003)Google Scholar
  11. 11.
    López-Rubio, E., Ortiz-de-Lazcano-Lobato, J.M., Vargas-González, M.C., López-Rubio, J.M.: Dynamic Selection of Model Parameters in Principal Components Analysis Neural Networks. In: Proceedings of the 16th European Conference on Artificial Intelligence (ECAI 2004), pp. 618–622 (2004)Google Scholar
  12. 12.
    López-Rubio, E., Ortiz-de-Lazcano-Lobato, J.M., Vargas-González, M.C.: Competitive Networks of Probabilistic Principal Components Analysis Neurons. In: 9th IASTED International Conference on Artificial Intelligence and Soft Computing (ASC 2005), pp. 141–146 (2005)Google Scholar
  13. 13.
    VizieR service (March 29, 2004), Online, Available at,
  14. 14.
    Chen, H.-W., et al.: Early-type galaxy progenitors beyond z=1. Astrophysical Journal 560, L131 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ezequiel López-Rubio
    • 1
  • Juan Miguel Ortiz-de-Lazcano-Lobato
    • 1
  • Domingo López-Rodríguez
    • 2
  • Enrique Mérida-Casermeiro
    • 2
  • María del Carmen Vargas-González
    • 1
  1. 1.Department of Computer Science and Artificial IntelligenceUniversity of MálagaMálagaSpain
  2. 2.Department of Applied MathematicsUniversity of MálagaMálagaSpain

Personalised recommendations