On Convergence of Approximate Message Passing - Archive ouverte HAL Access content directly
Journal Articles IEExplore Year : 2015

On Convergence of Approximate Message Passing

(1) , (2) , (1)
1
2

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, it was observed by several authors 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.

Dates and versions

cea-01223403 , version 1 (02-11-2015)

Identifiers

Cite

Francesco Caltagirone, Florent Krzakala, Lenka Zdeborová. On Convergence of Approximate Message Passing. IEExplore, 2015, ⟨10.1109/ISIT.2014.6875146⟩. ⟨cea-01223403⟩
92 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More