Markov Conditions and Factorization in Logical Credal Networks
This work addresses theoretical foundations for probabilistic graphical models in AI, but it appears incremental as it builds on existing frameworks without introducing new methods or broad applications.
The paper investigates Markov conditions in Logical Credal Networks, showing that acyclic structures lead to established factorization results, and analyzes differences in Markov conditions, factorization, and specifications for networks with cycles.
We examine the recently proposed language of Logical Credal Networks, in particular investigating the consequences of various Markov conditions. We introduce the notion of structure for a Logical Credal Network and show that a structure without directed cycles leads to a well-known factorization result. For networks with directed cycles, we analyze the differences between Markov conditions, factorization results, and specification requirements.