Inexact alternating optimization for phase retrieval with outliers

Cheng Qian, Xiao Fu, Nicholas D. Sidiropoulos, Lei Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Most of the available phase retrieval algorithms were explicitly or implicitly developed under a Gaussian noise model, using least squares (LS) formulations. However, in some applications of phase retrieval, an unknown subset of the measurements can be seriously corrupted by outliers, where LS is not robust and will degrade the estimation performance severely. This paper presents an Alternating Iterative Reweighted Least Squares (AIRLS) method for phase retrieval in the presence of such outliers. The AIRLS employs two-block alternating optimization to retrieve the signal through solving an ℓp-norm minimization problem, where 0 < p < 2. The Cramér-Rao bound (CRB) for Laplacian as well as Gaussian noise is derived for the measurement model considered, and simulations show that the proposed approach outperforms state-of-the-art algorithms in heavy-tailed noise.

Original languageEnglish (US)
Title of host publication2016 24th European Signal Processing Conference, EUSIPCO 2016
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages1538-1542
Number of pages5
ISBN (Electronic)9780992862657
DOIs
StatePublished - Nov 28 2016
Event24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary
Duration: Aug 28 2016Sep 2 2016

Publication series

NameEuropean Signal Processing Conference
Volume2016-November
ISSN (Print)2219-5491

Other

Other24th European Signal Processing Conference, EUSIPCO 2016
CountryHungary
CityBudapest
Period8/28/169/2/16

Keywords

  • Cramér-Rao bound (CRB)
  • Iterative Reweighted Least Squares
  • Phase retrieval

Cite this