Abstract
An algorithm for approximate credal network updating is presented. The problem in its general formulation is a multilinear optimization task, which can be linearized by an appropriate rule for fixing all the local models apart from those of a single variable. This simple idea can be iterated and quickly leads to very accurate inferences. The approach can also be specialized to classification with credal networks based on the maximality criterion. A complexity analysis for both the problem and the algorithm is reported together with numerical experiments, which confirm the good performance of the method. While the inner approximation produced by the algorithm gives rise to a classifier which might return a subset of the optimal class set, preliminary empirical results suggest that the accuracy of the optimal class set is seldom affected by the approximate probabilities.
This work was supported by the Swiss NSF grants nos. 200020_134759 / 1, 200020_137680 / 1, and by the Hasler foundation grant n. 10030.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Antonucci, A., Brühlmann, R., Piatti, A., Zaffalon, M.: Credal networks for military identification problems. Int. J. Approx. Reasoning 50(2), 666–679 (2009)
Antonucci, A., de Campos, C.P.: Decision making by credal nets. In: Proceedings of the International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC 2011), vol. 1, pp. 201–204. IEEE (2011)
Antonucci, A., Yi, S., de Campos, C.P., Zaffalon, M.: Generalized loopy 2U: a new algorithm for approximate inference in credal networks. Int. J. Approx. Reasoning 51(5), 474–484 (2010)
Cano, A., Gomez, M., Moral, S., Abellan, J.: Hill-climbing and branch-and-bound algorithms for exact and approximate inference in credal networks. Int. J. Approx. Reasoning 44(3), 261–280 (2007)
Cozman, F.G.: Credal networks. Artificial Intelligence 120, 199–233 (2000)
da Rocha, J.C.F., Cozman, F.G., de Campos, C.P.: Inference in polytrees with sets of probabilities. In: UAI 2003, pp. 217–224 (2003)
de Campos, C.P., Cozman, F.G.: Inference in credal networks using multilinear programming. In: Proceedings of the Second Starting AI Researcher Symposium, pp. 50–61. IOS Press, Amsterdam (2004)
de Campos, C.P., Cozman, F.G.: The inferential complexity of Bayesian and credal networks. In: Proceedings of the International Joint Conference on Artificial Intelligence, Edinburgh, pp. 1313–1318 (2005)
de Campos, C.P., Cozman, F.G.: Inference in credal networks through integer programming. In: International Symposium on Imprecise Probability: Theories and Applications (ISIPTA), Prague, pp. 145–154 (2007)
Ferreira da Rocha, J.C., Cozman, F.G.: Inference in credal networks: branch-and-bound methods and the A/R+ algorithm. Int. J. Approx. Reasoning 39(2-3), 279–296 (2005)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Lukatskii, A.M., Shapot, D.V.: Problems in multilinear programming. Computational Mathematics and Mathematical Physics 41(5), 638–648 (2000)
Mauà, D.D., de Campos, C.P., Zaffalon, M.: Updating credal networks is approximable in polynomial time. Int. J. Approx. Reasoning (2012)
Shafer, G.: A Mathematical Theory of Evidence. Princeton University Press (1976)
Walley, P.: Statistical Reasoning with Imprecise Probabilities. Chapman and Hall (1991)
Zaffalon, M.: The naive credal classifier. J. Stat. Plann. Inference 105(1), 5–21 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Antonucci, A., de Campos, C.P., Huber, D., Zaffalon, M. (2013). Approximating Credal Network Inferences by Linear Programming. In: van der Gaag, L.C. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2013. Lecture Notes in Computer Science(), vol 7958. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39091-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-39091-3_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39090-6
Online ISBN: 978-3-642-39091-3
eBook Packages: Computer ScienceComputer Science (R0)