A Logical Approach to Context-Specific Independence

Bayesian networks constitute a qualitative representation for conditional independence CI properties of a probability distribution. It is known that every CI statement implied by the topology of a Bayesian network G is witnessed over G under a graph-theoretic criterion called d-separation. Alternatively, all such implied CI statements have been shown to be derivable using the so-called semi-graphoid axioms. In this article we consider Labeled Directed Acyclic Graphs LDAG the purpose of which is to graphically model situations exhibiting context-specific independence CSI. We define an analogue of dependence logic suitable to express context-specific independence and study its basic properties. We also consider the problem of finding inference rules for deriving non-local CSI and CI statements that logically follow from the structure of a LDAG but are not explicitly encoded by it.

[1]  Dan Geiger,et al.  On the logic of causal models , 2013, UAI.

[2]  Erich Grädel,et al.  Dependence and Independence , 2012, Stud Logica.

[3]  A. Dawid.  Conditional Independence in Statistical Theory , 1979 .

[4]  Juha Kontinen,et al.  Axiomatizing first order consequences in dependence logic , 2012, Ann. Pure Appl. Log..

[5]  Marc Gyssens,et al.  On the conditional independence implication problem: A lattice-theoretic approach , 2008, Artif. Intell..

[6]  Sebastian Link,et al.  Sound approximate reasoning about saturated conditional probabilistic independence under controlled uncertainty , 2013, J. Appl. Log..

[7]  Jukka Corander,et al.  Context-Specific and Local Independence in Markovian Dependence Structures , 2016, Dependence Logic.

[8]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[9]  Judea Pearl,et al.  Causal networks: semantics and expressiveness , 2013, UAI.

[10]  Dan Geiger,et al.  Axioms and Algorithms for Inferences Involving Probabilistic Independence , 1991, Inf. Comput..

[11]  Dan Wu,et al.  On the implication problem for probabilistic conditional independency , 2000, IEEE Trans. Syst. Man Cybern. Part A.

[12]  Sebastian Link.  Frontiers for propositional reasoning about fragments of probabilistic conditional independence and hierarchical database decompositions , 2015, Theor. Comput. Sci..

[13]  Jouko A. Väänänen,et al.  Dependence Logic - A New Approach to Independence Friendly Logic , 2007, London Mathematical Society student texts.

[14]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[15]  Dan Geiger,et al.  Identifying independence in bayesian networks , 1990, Networks.

[16]  Sebastian Link,et al.  Reasoning about Saturated Conditional Independence Under Uncertainty: Axioms, Algorithms, and Levesque's Situations to the Rescue , 2013, AAAI.

[17]  Pietro Galliani,et al.  Inclusion and exclusion dependencies in team semantics - On some logics of imperfect information , 2011, Ann. Pure Appl. Log..

[18]  Miika Hannula.  Reasoning About Embedded Dependencies Using Inclusion Dependencies , 2015, LPAR.

[19]  Jukka Corander,et al.  Labeled directed acyclic graphs: a generalization of context-specific independence in directed graphical models , 2013, Data Mining and Knowledge Discovery.

[20]  Christian Herrmann.  On the Undecidability of Implications Between Embedded Multivalued Database Dependencies , 1995, Inf. Comput..

[21]  S. Sullivant.  Gaussian conditional independence relations have no finite complete characterization , 2007, 0704.2847.

[22]  Miika Hannula,et al.  Axiomatizing first-order consequences in independence logic , 2013, Ann. Pure Appl. Log..

[23]  Miika Hannula,et al.  A Finite Axiomatization of Conditional Independence and Inclusion Dependencies , 2014, FoIKS.

[24]  Marc Gyssens,et al.  On the completeness of the semigraphoid axioms for deriving arbitrary from saturated conditional independence statements , 2014, Inf. Process. Lett..

[25]  Craig Boutilier,et al.  Context-Specific Independence in Bayesian Networks , 1996, UAI.

[26]  Arne Meier,et al.  Approximation and Dependence via Multiteam Semantics , 2016, FoIKS.