Abstract
Variable Elimination (VE) answers a query posed to a Bayesian network (BN) by manipulating the conditional probability tables of the BN. Each successive query is answered in the same manner. In this paper, we present an inference algorithm that is aimed at maximizing the reuse of past computation but does not involve precomputation. Compared to VE and a variant of VE incorporating precomputation, our approach fairs favourably in preliminary experimental results.
Supported by NSERC Discovery Grant 238880.
Supported by CNPq - Science Without Borders.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann (1988)
Zhang, N.L., Poole, D.: A simple approach to Bayesian network computations. In: Proceedings of the Tenth Biennial Canadian Artificial Intelligence Conference, pp. 171–178 (1994)
Cozman, F.G.: Generalizing variable elimination in Bayesian networks. In: Workshop on Probabilistic Reasoning in Artificial Intelligence, Atibaia, Brazil (2000)
Shafer, G.: Probabilistic Expert Systems, vol. 67. Society for Industrial and Applied Mathematics, Philadelphia (1996)
Tarjan, R., Yannakakis, M.: Simple linear-time algorithms to test chordality of graphs, test acyclicity of hypergraphs, and selectively reduce acyclic hypergraphs. SIAM Journal on Computing 13(3), 566–579 (1984)
Butz, C.J., Yao, H., Hua, S.: A join tree probability propagation architecture for semantic modeling. Journal of Intelligent Information Systems 33(2), 145–178 (2009)
Butz, C.J., Yan, W.: The semantics of intermediate cpts in variable elimination. In: Fifth European Workshop on Probabilistic Graphical Models (2010)
Madsen, A.L., Butz, C.J.: Ordering arc-reversal operations when eliminating variables in Lazy AR propagation. International Journal of Approximate Reasoning 54(8), 1182–1196 (2013)
Madsen, A.L., Jensen, F.V.: Lazy propagation: A junction tree inference algorithm based on Lazy evaluation. Artificial Intelligence 113(1-2), 203–245 (1999)
Madsen, A.L.: Improvements to message computation in Lazy propagation. International Journal of Approximate Reasoning 51(5), 499–514 (2010)
Madsen, A.L., Butz, C.J.: On the importance of elimination heuristics in Lazy propagation. In: Sixth European Workshop on Probabilistic Graphical Models (PGM), pp. 227–234 (2012)
Butz, C.J., Hua, S., Konkel, K., Yao, H.: Join tree propagation with prioritized messages. Networks 55(4), 350–359 (2010)
Butz, C., Hua, S.: An improved Lazy-ar approach to Bayesian network inference. In: Nineteenth Canadian Conference on Artificial Intelligence (AI), pp. 183–194 (2006)
Butz, C.J., Konkel, K., Lingras, P.: Join tree propagation utilizing both arc reversal and variable elimination. International Journal of Approximate Reasoning 52(7), 948–959 (2011)
Butz, C.J., Chen, J., Konkel, K., Lingras, P.: A formal comparison of variable elimination and arc reversal in Bayesian network inference. Intelligent Decision Technologies 3(3), 173–180 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Butz, C.J., de S. Oliveira, J., Madsen, A.L. (2014). Bayesian Network Inference Using Marginal Trees. In: van der Gaag, L.C., Feelders, A.J. (eds) Probabilistic Graphical Models. PGM 2014. Lecture Notes in Computer Science(), vol 8754. Springer, Cham. https://doi.org/10.1007/978-3-319-11433-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-11433-0_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11432-3
Online ISBN: 978-3-319-11433-0
eBook Packages: Computer ScienceComputer Science (R0)