Translator Disclaimer
April 2015 Universality in polytope phase transitions and message passing algorithms
Mohsen Bayati, Marc Lelarge, Andrea Montanari
Ann. Appl. Probab. 25(2): 753-822 (April 2015). DOI: 10.1214/14-AAP1010

Abstract

We consider a class of nonlinear mappings $\mathsf{F}_{A,N}$ in $\mathbb{R}^{N}$ indexed by symmetric random matrices $A\in\mathbb{R}^{N\times N}$ with independent entries. Within spin glass theory, special cases of these mappings correspond to iterating the TAP equations and were studied by Bolthausen [Comm. Math. Phys. 325 (2014) 333–366]. Within information theory, they are known as “approximate message passing” algorithms.

We study the high-dimensional (large $N$) behavior of the iterates of $\mathsf{F}$ for polynomial functions $\mathsf{F}$, and prove that it is universal; that is, it depends only on the first two moments of the entries of $A$, under a sub-Gaussian tail condition. As an application, we prove the universality of a certain phase transition arising in polytope geometry and compressed sensing. This solves, for a broad class of random projections, a conjecture by David Donoho and Jared Tanner.

Citation

Download Citation

Mohsen Bayati. Marc Lelarge. Andrea Montanari. "Universality in polytope phase transitions and message passing algorithms." Ann. Appl. Probab. 25 (2) 753 - 822, April 2015. https://doi.org/10.1214/14-AAP1010

Information

Published: April 2015
First available in Project Euclid: 19 February 2015

zbMATH: 1322.60207
MathSciNet: MR3313755
Digital Object Identifier: 10.1214/14-AAP1010

Subjects:
Primary: 60F05
Secondary: 68W40

Rights: Copyright © 2015 Institute of Mathematical Statistics

JOURNAL ARTICLE
70 PAGES


SHARE
Vol.25 • No. 2 • April 2015
Back to Top