Work

On convergence of approximate message passing

Year: 2014

Type: conference-paper

Abstract: Approximate message passing is an iterative algorithm for compressed sensing and related applications. A solid theory about the performance and convergence of the algorithm exists for measurement matrices having iid entries of zero mean. However, several authors have observed that for more general matrices the algorithm often encounters convergence problems. In this paper we identify the reason of the non-convergence for measurement matrices with iid entries and non-zero mean in the context of Bayes optimal inference. Finally we demonstrate numerically that when the iterative update is changed from parallel to sequential the convergence is restored.

Source: IEEE International Symposium on Information Theory (ISIT)

DOI: 10.1109/isit.2014.6875146

Authors: Francesco Caltagirone, Lenka Zdeborova, Florent Krzakala

Institutions: Centre National de la Recherche Scientifique, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Institut de Physique Théorique, Université Pierre-et-Marie-Curie

Language: English

Topic: Sparse and Compressive Sensing Techniques

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2148486648

FWCI: 13.83

Cites: 14

Cited by: 83

Related to: