The Local Inconsistency Resolution Algorithm
Keywords: probabilistic dependency graphs, approximate inference, learning, message passing, gradient flow, attention, control
TL;DR: a generic unifying algorithm for local learning and inference
Abstract: 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.
Submission Number: 112
Loading