On the completeness of the semigraphoid axioms for deriving arbitrary from saturated conditional independence statements.
Marc GyssensMathias NiepertDirk Van GuchtPublished in: Inf. Process. Lett. (2014)
Keyphrases
- conditional independence
- axiomatic characterization
- bayesian networks
- random variables
- graphical models
- probability distribution
- learning bayesian networks
- causal models
- structure learning
- directed acyclic graph
- gaussian model
- statistical independence
- structure and parameter learning
- probability theory
- possibility theory
- bayesian network structure
- incomplete information
- probabilistic model
- image segmentation
- mutual information
- causal independence
- conditional independencies
- chain graphs