Abstract

We elaborate on hierarchical credal sets, which are sets of probability mass functions paired with second-order distributions. A new criterion to make decisions based on these models is proposed. This is achieved by sampling from the set of mass functions and considering the Kullback-Leibler divergence from the weighted center of mass of the set. We evaluate this criterion in a simple classification scenario: the results show performance improvements when compared to a credal classifier where the second-order distribution is not taken into account.

Keywords

Credal sets second-order models hierarchical credal sets shifted Dirichlet distribution credal classification decision making 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bernardo, J.M., Smith, F.M.: Bayesian Theory. John Wiley and Sons (2000)Google Scholar
  2. 2.
    Cano, A., Cano, J., Moral, S.: Convex sets of probabilities propagation by simulated annealing on a tree of cliques. In: Bouchon-Meunier, B., Yager, R.R., Zadeh, L.A. (eds.) IPMU 1994. LNCS, vol. 945, pp. 978–983. Springer, Heidelberg (1995)Google Scholar
  3. 3.
    de Campos, L., Huete, J., Moral, S.: Probability intervals: A tool for uncertain reasoning. Int. Journ. of Unc., Fuzz. and Knowledge-Based Syst. 2, 167–196 (1994)CrossRefMATHGoogle Scholar
  4. 4.
    Gärdenfors, P., Sahlin, N.: Unreliable probabilities, risk taking, and decision making. Synthese 53, 361–386 (1982)CrossRefMATHMathSciNetGoogle Scholar
  5. 5.
    Karlsson, A., Sundgren, D.: Evaluation of evidential combination operators. In: Proceedings of ISIPTA 2013 (2013)Google Scholar
  6. 6.
    Karlsson, A., Sundgren, D.: Second-order credal combination of evidence. In: Proceedings of ISIPTA 2013 (2013)Google Scholar
  7. 7.
    Lovász, L.: Hit-and-run mixes fast. Math. Programming 86(3), 443–461 (1999)CrossRefMATHGoogle Scholar
  8. 8.
    Shafer, G.: A Mathematical Theory of Evidence. Princeton University Press (1976)Google Scholar
  9. 9.
    Sundgren, D., Karlsson, A.: On dependence in second-order probability. In: Hüllermeier, E., Link, S., Fober, T., Seeger, B. (eds.) SUM 2012. LNCS, vol. 7520, pp. 379–391. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  10. 10.
    Tervonen, T., van Valkenhoef, G., Basturk, N., Postmus, D.: Hit-and-run enables efficient weight generation for simulation-based multiple criteria decision analysis. European Journal of Operational Research 224(3), 552–559 (2013)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Walley, P.: Statistical Reasoning with Imprecise Probabilities. Chapman and Hall (1991)Google Scholar
  12. 12.
    Walley, P.: Inferences from multinomial data: learning about a bag of marbles. Journal of the Royal Statistical Society. Series B (Methodological) 58, 3–57 (1996)MATHMathSciNetGoogle Scholar
  13. 13.
    Zaffalon, M., Corani, G., Mauá, D.D.: Evaluating credal classifiers by utility-discounted predictive accuracy. International Journal of Approximate Reasoning 53(8), 1282–1301 (2012)CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Alessandro Antonucci
    • 1
  • Alexander Karlsson
    • 2
  • David Sundgren
    • 3
  1. 1.Istituto Dalle Molle di Studi sull’Intelligenza ArtificialeManno-LuganoSwitzerland
  2. 2.Informatics Research CenterUniversity of SkövdeSweden
  3. 3.Department of Computer and Systems SciencesStockholm UniversitySweden

Personalised recommendations