Work

Variational free energies for compressed sensing

Year: 2014

Type: conference-paper

Abstract: We consider a variational free energy approach for compressed sensing. We first show that the naïve mean field approach performs remarkably well when coupled with a noise learning procedure. We also notice that it leads to the same equations as those used for iterative thresholding.We then discuss the Bethe free energy and how it corresponds to the fixed points of the approximate message passing algorithm. In both cases, we test numerically the direct optimization of the free energies as a converging sparse-estimation algorithm. We further derive the Bethe free energy in the context of generalized approximate message passing.

Source: IEEE International Symposium on Information Theory (ISIT)

DOI: 10.1109/isit.2014.6875083

Authors: Florent Krzakala, Andre Manoel, Eric W. Tramel, Lenka Zdeborova

Institutions: Centre National de la Recherche Scientifique, École Normale Supérieure - PSL, Gulliver, Institut de Physique Théorique

Language: English

Topic: Sparse and Compressive Sensing Techniques

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1985715224

FWCI: 11.4

Cites: 16

Cited by: 36

Related to: