A newton-type forward backward greedy method for multi-Snapshot compressed sensing

Bazzi, Ahmad; Slock, Dirk T.M; Meilhac, Lisa
ASILOMAR 2017, Asilomar Conference on Signals, Systels, and Computers, October 29th-November 1st, 2017, Pacific Grove, CA, USA

Parameter estimation has applications in many applications of signal processing, such as Angle-of-Arrival (AoA) estimation. Compressed sensing is a widely growing paradigm that can be applied to parameter estimation via sparse recovery. In this paper, we propose
a Newton-type Forward Backward Greedy method that performs sparse recovery, given the observed data over multiple snapshots. This method is applied to the AoA
estimation problem, where we have observed better performance, in terms of Mean-Squared Error and faster convergence when compared to existing methods. More
information can be found in the conclusions section.

Pacific Grove
Systèmes de Communication
Eurecom Ref:
© 2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/5272