Reconsidering Dependency Networks from an Information Geometry Perspective

ArXi:2604.01117v1 Announce Type: new Dependency networks (Heckerman, 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their computational advantages over Bayesian and Marko networks, the theoretical foundations of dependency networks remain incomplete, primarily because their model distributions -- defined as stationary distributions of pseudo-Gibbs sampling -- lack closed-form expressions.