Learning in Deep Factor Graphs with Gaussian Belief Propagation

arXiv:2311.14649v2 Announce Type: replace
Abstract: We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with different observed nodes. Our experiments show that these problems can be efficiently solved with belief propagation (BP), whose updates are inherently local, presenting exciting opportunities for distributed and asynchronous training. Our approach can be scaled to deep networks …

abstract arxiv belief cs.lg graphs inference inputs nodes parameters prediction propagation random show stat.ml training type variables view