Abstract

The naive credal classifier (NCC) extends naive Bayes classifier (NBC) to imprecise probabilities to robustly deal with the specification of the prior; NCC models a state of ignorance by using a set of priors, which is formalized by Walley’s Imprecise Dirichlet Model (IDM). NCC has been shown to return more robust classification than NBC. However, there are particular situations (which we precisely characterize in the paper) under which the extreme densities included by the IDM force NCC to become very indeterminate, although NBC is able to issue accurately classifications. In this paper, we propose two approaches which overcome this issue, by restricting the set of priors of the IDM . We analyze both approaches theoretically and experimentally.

Keywords

Class Problem Bayesian Model Average Feature Problem Prior Density Bayesian Model Average 
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.
    Benavoli, A., de Campos, C.P.: Inference from multinomial data based on a MLE-dominance criterion. In: Proc. of the 10th European Conf. on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, pp. 22–33. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Bernard, J.-M.: An introduction to the Imprecise Dirichlet Model for multinomial data. Int. J. of Approximate Reasoning 39(2-3), 123–150 (2005)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Corani, G., Zaffalon, M.: Credal Model Averaging: An Extension of Bayesian Model Averaging to Imprecise Probabilities. In: Proc. of the 2008 European Conf. on Machine Learning and Knowledge Discovery in Databases, pp. 257–271 (2008)Google Scholar
  4. 4.
    Corani, G., Zaffalon, M.: Lazy naive credal classifier. In: Proc. of the 1st ACM SIGKDD Workshop on Knowledge Discovery from Uncertain Data, pp. 30–37. ACM, New York (2009)CrossRefGoogle Scholar
  5. 5.
    Dash, D., Cooper, G.F.: Model Averaging for Prediction with Discrete Bayesian Networks. J. of Machine Learning Research 5, 1177–1203 (2004)MathSciNetMATHGoogle Scholar
  6. 6.
    Walley, P.: Statistical Reasoning with Imprecise Probabilities. Chapman and Hall, New York (1991)CrossRefMATHGoogle Scholar
  7. 7.
    Zaffalon, M.: Statistical inference of the naive credal classifier. In: ISIPTA 2001: Proc. of the Second Int. Symp. on Imprecise Probabilities and Their Applications, The Netherlands, Shaker, pp. 384–393 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Giorgio Corani
    • 1
  • Alessio Benavoli
    • 1
  1. 1.Istituto Dalle Molle di Studi sull’Intelligenza ArtificialeMannoSwitzerland

Personalised recommendations