Volume 38, Issue 1
The Global Landscape of Phase Retrieval II: Quotient Intensity Models

Jian-Feng Cai, Meng Huang, Dong Li & Yang Wang

Ann. Appl. Math., 38 (2022), pp. 62-114.

Published online: 2022-01

Export citation
  • 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.

  • AMS Subject Headings

94A12, 65K10, 49K45

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{AAM-38-62, author = {Cai , Jian-FengHuang , MengLi , Dong and Wang , Yang}, title = {The Global Landscape of Phase Retrieval II: Quotient Intensity Models}, journal = {Annals of Applied Mathematics}, year = {2022}, volume = {38}, number = {1}, pages = {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.

}, issn = {}, doi = {https://doi.org/10.4208/aam.OA-2021-0010}, url = {http://global-sci.org/intro/article_detail/aam/20173.html} }
TY - JOUR T1 - The Global Landscape of Phase Retrieval II: Quotient Intensity Models AU - Cai , Jian-Feng AU - Huang , Meng AU - Li , Dong AU - Wang , Yang JO - Annals of Applied Mathematics VL - 1 SP - 62 EP - 114 PY - 2022 DA - 2022/01 SN - 38 DO - http://doi.org/10.4208/aam.OA-2021-0010 UR - https://global-sci.org/intro/article_detail/aam/20173.html KW - Phase retrieval, landscape analysis, non-convex optimization. AB -

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.

Cai , Jian-FengHuang , MengLi , Dong and Wang , Yang. (2022). The Global Landscape of Phase Retrieval II: Quotient Intensity Models. Annals of Applied Mathematics. 38 (1). 62-114. doi:10.4208/aam.OA-2021-0010
Copy to clipboard
The citation has been copied to your clipboard