By Topic

Universality in polytope phase transitions and iterative algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Bayati, M. ; Grad. Sch. of Bus., Stanford Univ., Stanford, CA, USA ; Lelarge, M. ; Montanari, A.

We consider a class of nonlinear mappings FA, N in RN indexed by symmetric random matrices A ϵ RN×N with independent entries. Within spin glass theory, special cases of these mappings correspond to iterating the TAP equations and were studied by Erwin Bolthausen. Within information theory, they are known as `approximate message passing' algorithms. We study the high-dimensional (large N) behavior of the iterates of F for polynomial functions F, and prove that it is universal, i.e. it depends only on the first two moments of the entries of A. As an application, we prove the universality of a certain phase transition arising in polytope geometry and compressed sensing. This solves a conjecture by David Donoho and Jared Tanner.

Published in:

Information Theory Proceedings (ISIT), 2012 IEEE International Symposium on

Date of Conference:

1-6 July 2012