Poster
in
Workshop: Localized Learning: Decentralized Model Updates via Non-Global Objectives

The Local Inconsistency Resolution Algorithm

Oliver Richardson

Keywords: Learning Approximate Inference conrol attention message passing probabilistic dependency graphs gradient flow

Project Page [ Poster] [ OpenReview]

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, which can capture inconsistent beliefs.

Chat is not available.