Year: 2022
Author: Jian-Feng Cai, Meng Huang, Dong Li, Yang Wang
Annals of Applied Mathematics, Vol. 38 (2022), Iss. 1 : pp. 62–114
Abstract
A fundamental problem in phase retrieval is to reconstruct an unknown signal from a set of magnitude-only measurements. In this work we introduce three novel quotient intensity models (QIMs) based on a deep modification of the traditional intensity-based models. A remarkable feature of the new loss functions is that the corresponding geometric landscape is benign under the optimal sampling complexity. When the measurements $ a_i\in \mathbb{R}^n$ are Gaussian random vectors and the number of measurements $m\ge Cn$, the QIMs admit no spurious local minimizers with high probability, i.e., the target solution $x$ is the unique local minimizer (up to a global phase) and the loss function has a negative directional curvature around each saddle point. Such benign geometric landscape allows the gradient descent methods to find the global solution $x$ (up to a global phase) without spectral initialization.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/aam.OA-2021-0010
Annals of Applied Mathematics, Vol. 38 (2022), Iss. 1 : pp. 62–114
Published online: 2022-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 53
Keywords: Phase retrieval landscape analysis non-convex optimization.
Author Details
-
Nearly optimal bounds for the global geometric landscape of phase retrieval
Cai, Jian-Feng | Huang, Meng | Li, Dong | Wang, YangInverse Problems, Vol. 39 (2023), Iss. 7 P.075011
https://doi.org/10.1088/1361-6420/acdab7 [Citations: 2] -
Provable sample-efficient sparse phase retrieval initialized by truncated power method
Cai, Jian-Feng | Li, Jingyang | You, JuntaoInverse Problems, Vol. 39 (2023), Iss. 7 P.075008
https://doi.org/10.1088/1361-6420/acd8b8 [Citations: 1]