Advertisement

Optimality of Kernel Density Estimation of Prior Distribution in Bayes Network

  • Hengqing Tong
  • Yanfang Deng
  • Ziling Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)

Abstract

The key problem of inductive-learning in Bayes network is the estimator of prior distribution. This paper adopts general naive Bayes to handle continuous variables, and proposes a kind of kernel function constructed by orthogonal polynomials, which is used to estimate the density function of prior distribution in Bayes network. The paper then makes further researches into optimality of the kernel estimation of density and derivatives. When the sample is fixed, the estimators can keep continuity and smoothness, and when the sample size tends to infinity, the estimators can keep good convergence rates.

Keywords

Kernel Function Prior Distribution Orthogonal Polynomial Total Space Kernel Density Estimation 
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.
    Zhang, H., Ling, C.: Numeric mapping and learnability of naive Bayes. Applied Artificial Intelligence 17, 507–518 (2003)CrossRefGoogle Scholar
  2. 2.
    Tang, Y., Pan, W.M., Li, H.M.: Fuzzy native Bayes classifier Based on fuzzy clustering. In: Proceedings of the IEEE International Conference on Systems, vol. 5, pp. 452–458 (2002)Google Scholar
  3. 3.
    Li, X.S., Li, D.Y.: A New Method Based on Density Clustering for Discretization of Continuous Attributes. Acta Simulata Systematica Sinica 6, 804–809 (2003)Google Scholar
  4. 4.
    Dougherty, J., Kohavi, R., Sahami, M.: Supervised and unsupervised discretization of continuous features. In: Proc. of the 12th International Conference on Machine Learning, pp. 194–202. Morgan Kaufmann Publishers, San Francisco (2003)Google Scholar
  5. 5.
    Li, B.C., Yuan, S.M., Wang, L.M.: The Simplified Expression of Bayesian Network. Chinese Journal of Scientific Instrument 10, 1070–1073 (2005)Google Scholar
  6. 6.
    Lin, P.E.: Rates of convergence in empirical Bayes estimation problems: continuous case. Ann. Statist. 3, 155–164 (1975)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Ronald, R.Y.: An extension of the naive Bayesian classifier. Information Sciences 176(5), 577–588 (2006)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Eugene, S., Yan, V.: Universal results for correlations of characteristic polynomials: Riemann-Hilbert approach. Communications in Mathematical Physics 241, 343–382 (2003)MATHMathSciNetGoogle Scholar
  9. 9.
    Freilikher, V., Kanzieper, E., Yurkevich, I.: Theory of random matrices with strong level confinement: orthogonal polynomial approach. Physical Review E 54, 210–219 (1996)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Gajek, L.: On improving density estimators which are not bona fide functions. Ann. Statist. 11, 1612–1618 (1986)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Roder, H., et al.: Kernel polynomial method for a nonorthogonal electronicstructure calculation of amorphous diamond. Physical Review B 55, 15382–15385 (1997)CrossRefGoogle Scholar
  12. 12.
    Li, J.J., Gupta, S.S.: Empirical Bayes tests based on kernel sequence estimation. Statistica Sinica 12, 1061–1072 (2002)MATHMathSciNetGoogle Scholar
  13. 13.
    Jones, M.C.: On kernel density derivative estimation. Communications in Statistics (Theory and Methods) 23, 2133–2139 (1994)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Girolami, M.: Orthogonal series density estimation and the kernel eigenvalue problem. Neural Computation 14, 669–688 (2002)MATHCrossRefGoogle Scholar
  15. 15.
    Messer, K.: A comparison of spline estimate to its equivalent kernel estimate. Ann. Statist. 19, 817–829 (1991)MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Parzen, E.: On estimation of a probability density function and model. Ann. Math. Statist. 33, 1065–1076 (1962)MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Tong, H.Q.: Convergence rates for empirical Bayes estimators of parameters in multi-parameter exponential families. Communications in Statistics (Theory and Methods) 25, 1089–1098 (1996)MATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Vanlessen, M.: Universal behavior for averages of characteristic polynomials at the origin of the spectrum. Communications in Mathematical Physics 253, 535–560 (2005)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hengqing Tong
    • 1
  • Yanfang Deng
    • 1
  • Ziling Li
    • 1
  1. 1.Department of MathematicsWuhan University of TechnologyWuhan, HubeiChina

Personalised recommendations