Poster
in
Workshop: Structured Probabilistic Inference and Generative Modeling
The Local Inconsistency Resolution Algorithm
Oliver Richardson
Keywords: [ gradient flow ] [ probabilistic dependency graphs ] [ message passing ] [ attention ] [ Approximate Inference ] [ Learning ] [ control ]
We present a generic algorithm for learning and approximate inference across a broad class of statistical models, that unifies many approaches in the literature. Our algorithm, called local inconsistency resolution (LIR), has an intuitive epistemic interpretation. It is based on the theory of probabilistic dependency graphs (PDGs), an expressive class of graphical models rooted in information theory, that can capture inconsistent beliefs.