Title
Optimization-Based AMP for Phase Retrieval: The Impact of Initialization and $\ell_{2}$ Regularization.
Abstract
We consider an ℓ2-regularized non-convex optimization problem for recovering signals from their noisy phaseless observations. We design and study the performance of a message passing algorithm that aims to solve this optimization problem. We consider the asymptotic setting m, n → ∞, m/n → δ and obtain sharp performance bounds, where m is the number of measurements and n is the signal dimension. We...
Year
DOI
Venue
2019
10.1109/TIT.2019.2893254
IEEE Transactions on Information Theory
Keywords
Field
DocType
Noise measurement,Optimization,Message passing,Iterative methods,Convex functions,Mean square error methods,Approximation algorithms
Discrete mathematics,Phase retrieval,Computer science,Algorithm,Regularization (mathematics),Initialization,Optimization problem,Message passing
Journal
Volume
Issue
ISSN
65
6
0018-9448
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Junjie Ma114815.24
Ji Xu2579.84
Arian Maleki380357.52