Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
On characterizing Inclusion of Bayesian Networks
Tomas Kocka, Remco Bouckaert, Milan Studeny
Abstract:
Every directed acyclic graph (DAG) over a finite non-empty set of variables (= nodes) N induces an independence model over N, which is a list of conditional independence statements over N.The inclusion problem is how to characterize (in graphical terms) whether all independence statements in the model induced by a DAG K are in the model induced by a second DAG L. Meek (1997) conjectured that this inclusion holds iff there exists a sequence of DAGs from L to K such that only certain 'legal' arrow reversal and 'legal' arrow adding operations are performed to get the next DAG in the sequence.In this paper we give several characterizations of inclusion of DAG models and verify Meek's conjecture in the case that the DAGs K and L differ in at most one adjacency. As a warming up a rigorous proof of well-known graphical characterizations of equivalence of DAGs, which is a highly related problem, is given.
Keywords: bayesian network, conditional independence, inclusion problem, learning graphical mod
Pages: 261-268
PS Link:
PDF Link: /papers/01/p261-kocka.pdf
BibTex:
@INPROCEEDINGS{Kocka01,
AUTHOR = "Tomas Kocka and Remco Bouckaert and Milan Studeny",
TITLE = "On characterizing Inclusion of Bayesian Networks",
BOOKTITLE = "Proceedings of the Seventeenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-01)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2001",
PAGES = "261--268"
}


hosted by DSL   •   site info   •   help