Regionalized Optimization

TL;DR

This paper introduces a mathematical framework for reconstructing global loss functions from local ones using functors, enabling new message passing algorithms for complex optimization problems with multiple perspectives.

Contribution

It presents a novel theoretical framework for regionalized loss reconstruction and connects it to existing and new message passing algorithms for diverse optimization scenarios.

Findings

Framework unifies various message passing algorithms.

New algorithms for noisy channel networks.

Shows how to derive critical points of regionalized losses.

Abstract

We propose a theoretical framework for non redundant reconstruction of a global loss from a collection of local ones under constraints given by a functor; we call this loss the regionalized loss in honor to Yedidia, Freeman, Weiss' celebrated article `Constructing free-energy approximations and generalized belief propagation algorithms' where a first example of regionalized loss, for entropy and the marginal functor, is built. We show how one can associate to these regionalized losses message passing algorithms for finding their critical points. It is a natural mathematical framework for optimization problems where there are multiple points of views on a dataset and replaces message passing algorithms as canonical ways of finding the optima of these problems. We explain how Generalized Belief propagation algorithms fall into the framework we propose and propose novel message passing algorithms for noisy channel networks.