Abstract
We adapt the theory of descriptive complexity to Bayesian networks, by investigating how expressive can be specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ first-order quantification capture the complexity class \(\mathsf {PP}\); that is, any phenomenon that can be simulated with a polynomial time probabilistic Turing machine can be also modeled by such a network. We also show that, by allowing quantification over predicates, the resulting Bayesian network specifications capture the complexity class \(\mathsf {PP}^\mathsf {NP}\), a result that does not seem to have equivalent in the literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., Halpern, J.Y.: Decidability and expressiveness for first-order logics of probability. Inf. Comput. 112(1), 1–36 (1994)
Cozman, F.G., Mauá, D.D.: Bayesian networks specified using propositional and relational constructs: Combined, data, and domain complexity. In: AAAI Conference on Artificial Intelligence (2015)
Cozman, F.G., Polastro, R.B.: Complexity analysis and variational inference for interpretation-based probabilistic description logics. In: Conference on Uncertainty in Artificial Intelligence, pp. 117–125 (2009)
Ebbinghaus, H.-D., Flum, J.: Finite Model Theory. Springer, Heidelberg (1995)
Enderton, H.B.: A Mathematical Introduction to Logic. Academic Press, Cambridge (1972)
Gaifman, H.: Concerning measures on first-order calculi. Isr. J. Math. 2, 1–18 (1964)
Getoor, L., Taskar, B.: Introduction to Statistical Relational Learning. MIT Press, Cambridge (2007)
Grädel, E.: Finite model theory and descriptive complexity. In: Grädel, E. (ed.) Finite Model Theory and its Applications, pp. 125–229. Springer, Heidelberg (2007)
Grädel, E.E., Kolaitis, P.G., Libkin, L., Marx, M., Spencer, J., Vardi, M.Y., Venema, Y., Weinstein, S.: Finite Model Theory and its Applications. Springer, Heidelberg (2007)
Jaeger, M.: Lower complexity bounds for lifted inference. Theor. Pract. Logic Program. 15(2), 246–264 (2014)
Koller, D., Friedman, N., Models, P.G.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Libkin, L.: Elements of Finite Model Theory. Springer, Heidelberg (2004)
Papadimitriou, C.H.: Computational Complexity. Addison-Wesley, Boston (1994)
Poole, D.: Probabilistic programming languages: independent choices and deterministic systems. In: Dechter, R., Geffner, H., Halpern, J.Y. (eds.) Heuristics, Probability and Causality - A Tribute to Judea Pearl, pp. 253–269. College Publications, London (2010)
De Raedt, L.: Logical and Relational Learning. Springer, Heidelberg (2008)
De Raedt, L., Frasconi, P., Kersting, K., Muggleton, S.: Probabilistic Inductive Logic Programming. Springer, Heidelberg (2010)
Saluja, S., Subrahmanyam, K.V.: Descriptive complexity of #P functions. J. Comput. Syst. Sci. 50, 493–505 (1995)
Van den Broeck, G.: On the completeness of first-order knowledge compilation for lifted probabilistic inference. In: Neural Processing Information Systems, pp. 1386–1394 (2011)
Wagner, K.W.: The complexity of combinatorial problems with succinct input representation. Acta Informatica 23, 325–356 (1986)
Acknowledgements
The first author is partially supported by CNPq, grant 308433/2014-9. This paper was partially funded by FAPESP grant #2015/21880-4 (project Proverbs).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cozman, F.G., Mauá, D.D. (2017). The Descriptive Complexity of Bayesian Network Specifications. In: Antonucci, A., Cholvy, L., Papini, O. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2017. Lecture Notes in Computer Science(), vol 10369. Springer, Cham. https://doi.org/10.1007/978-3-319-61581-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-61581-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61580-6
Online ISBN: 978-3-319-61581-3
eBook Packages: Computer ScienceComputer Science (R0)