Abstract
The implication problem of conditional statements about the independence of finitely many sets of random variables is studied in the presence of controlled uncertainty. Uncertainty refers to the possibility of missing data. As a control mechanism random variables can be declared complete, in which case data on these random variables cannot be missing. While the implication of conditional independence statements is not axiomatizable, a finite Horn axiomatization is established for the expressive class of saturated conditional independence statements under controlled uncertainty. Complete random variables allow us to balance the expressivity of sets of saturated statements with the efficiency of deciding their implication. This ability can soundly approximate reasoning in the absence of missing data. Delobel’s class of full first-order hierarchical database decompositions are generalized to the presence of controlled uncertainty, and their implication problem shown to be equivalent to that of saturated conditional independence.
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
Atzeni, P., Morfuni, N.: Functional dependencies and constraints on null values in database relations. Information and Control 70(1), 1–31 (1986)
Batista, G., Monard, M.: An analysis of four missing data treatment methods for supervised learning. Applied Artificial Intelligence 17(5-6), 519–533 (2003)
Biskup, J., Hartmann, S., Link, S.: Probabilistic conditional independence under schema certainty and uncertainty. In: Hüllermeier, E., Link, S., Fober, T., Seeger, B. (eds.) SUM 2012. LNCS, vol. 7520, pp. 365–378. Springer, Heidelberg (2012)
Chickering, D., Heckerman, D.: Efficient approximations for the marginal likelihood of Bayesian networks with hidden variables. Machine Learning 29(2-3), 181–212 (1997)
Darwiche, A.: Modeling and Reasoning with Bayesian Networks. Cambridge University Press (2009)
Dawid, A.: Conditional independence in statistical theory. Journal of the Royal Statistical Society 41(1), 1–31 (1979)
Delobel, C.: Normalization and hierarchical dependencies in the relational data model. ACM Trans. Database Syst. 3(3), 201–222 (1978)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society B 39, 139 (1977)
Fayyad, U., Piatetsky-Shapiro, G., Smyth, P.: From data mining to knowledge discovery in databases. AI Magazine 17(3), 37–54 (1996)
Ferrarotti, F., Hartmann, S., Link, S.: Reasoning about functional and full hierarchical dependencies over partial relations. Inf. Sci. 235, 150–173 (2013)
Friedman, N.: Learning belief networks in the presence of missing values and hidden variables. In: ICML, pp. 125–133 (1997)
Galil, Z.: An almost linear-time algorithm for computing a dependency basis in a relational database. J. ACM 29(1), 96–102 (1982)
Geiger, D., Pearl, J.: Logical and algorithmic properties of conditional independence and graphical models. The Annals of Statistics 21(4), 2001–2021 (1993)
Geiger, D., Pearl, J.: Logical and algorithmic properties of independence and their application to Bayesian networks. Ann. Math. Artif. Intell. 2, 165–178 (1990)
Grädel, E., Väänänen, J.: Dependence and independence. Studia Logica 101(2), 399–410 (2012)
Graetzer, G.: General lattice theory. Birkhäuser, Boston (1998)
Halpern, J.: Reasoning about uncertainty. MIT Press (2005)
Hartmann, S., Link, S.: The implication problem of data dependencies over SQL table definitions: axiomatic, algorithmic and logical characterizations. ACM Trans. Database Syst. 37(2), Article 13 (2012)
Herrmann, C.: Corrigendum to “On the undecidability of implications between embedded multivalued database dependencies”. Inf. Comput. 204(12), 1847–1851 (2006)
Kontinen, J., Link, S., Väänänen, J.: Independence in database relations. In: Libkin, L. (ed.) WoLLIC 2013. LNCS, vol. 8071, pp. 179–193. Springer, Heidelberg (2013)
Lauritzen, S.: The EM algorithm for graphical association models with missing data. Computational Statistics and Data Analysis 19, 191–201 (1995)
Lien, E.: On the equivalence of database models. J. ACM 29(2), 333–362 (1982)
Link, S.: Propositional reasoning about saturated conditional probabilistic independence. In: Ong, L., de Queiroz, R. (eds.) WoLLIC 2012. LNCS, vol. 7456, pp. 257–267. Springer, Heidelberg (2012)
Link, S.: Reasoning about saturated conditional independence under uncertainty: Axioms, algorithms, and Levesque’s situations to the rescue. AAAI (2013)
Link, S.: Sound approximate reasoning about saturated probabilistic conditional independence under controlled uncertainty. J. Applied Logic (2013), http://dx.doi.org/10.1016/j.jal.2013.05.004
Marlin, B., Zemel, R., Roweis, S., Slaney, M.: Recommender systems, missing data and statistical model estimation. In: IJCAI, pp. 2686–2691 (2011)
Matúš, F.: Ascending and descending conditional independence relations. In: Transactions of the 11th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, pp. 189–200 (1992)
Niepert, M., Van Gucht, D., Gyssens, M.: Logical and algorithmic properties of stable conditional independence. Int. J. Approx. Reasoning 51(5), 531–543 (2010)
Niepert, M., Van Gucht, D., Gyssens, M.: On the conditional independence implication problem: A lattice-theoretic approach. In: UAI, pp. 435–443 (2008)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)
Singh, M.: Learning Bayesian networks from incomplete data. In: AAAI, pp. 534–539 (1997)
Stott Parker Jr., D., Parsaye-Ghomi, K.: Inferences involving embedded multivalued dependencies and transitive dependencies. In: SIGMOD, pp. 52–57 (1980)
Studený, M.: Conditional independence relations have no finite complete characterization. In: Transactions of the 11th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, pp. 377–396 (1992)
Thiesson, B.: Accelerated quantification of bayesian networks with incomplete data. In: KDD, pp. 306–311 (1995)
de Waal, P., van der Gaag, L.: Stable independence in perfect maps. In: UAI, pp. 161–168 (2005)
Wong, S., Butz, C., Wu, D.: On the implication problem for probabilistic conditional independency. IEEE Trans. Systems, Man, and Cybernetics, Part A: Systems and Humans 30(6), 785–805 (2000)
Zaniolo, C.: Database relations with null values. J. Comput. Syst. Sci. 28(1), 142–166 (1984)
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
Link, S. (2013). Approximate Reasoning about Generalized Conditional Independence with Complete Random Variables. In: Liu, W., Subrahmanian, V.S., Wijsen, J. (eds) Scalable Uncertainty Management. SUM 2013. Lecture Notes in Computer Science(), vol 8078. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40381-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-40381-1_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40380-4
Online ISBN: 978-3-642-40381-1
eBook Packages: Computer ScienceComputer Science (R0)