Sample-Efficient Low Rank Phase Retrieval

DOI10.1109/TIT.2021.3112805MaRDI QIDQ5032652zbMATH OpenOpenAlexFDO

Authors Seyedehsara Nayer, Namrata Vaswani

Publication date 17 February 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.06198

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: This work studies the Low Rank Phase Retrieval (LRPR) problem: recover an $nimesq$ rank-$r$ matrix $X^{\ast }$ from $y_k=|A_k^{o}p{x}_k^{\ast }|$, $k=1,2,\mathrm{...},q$, when each $y_k$ is an m-length vector containing independent phaseless linear projections of $x_k^{\ast }$. The different matrices $A_k$ are i.i.d. and each contains i.i.d. standard Gaussian entries. We obtain an improved guarantee for AltMinLowRaP, which is an Alternating Minimization solution to LRPR that was introduced and studied in our recent work. As long as the right singular vectors of $X^{\ast }$ satisfy the incoherence assumption, we can show that the AltMinLowRaP estimate converges geometrically to $X^{\ast }$ if the total number of measurements $mqgtrsimn{r}^2(r+log(1/epsilon))$. In addition, we also need $mgtrsimmax(r,logq,logn)$ because of the specific asymmetric nature of our problem. Compared to our recent work, we improve the sample complexity of the AltMin iterations by a factor of $r^2$, and that of the initialization by a factor of $r$. We also extend our result to the noisy case; we prove stability to corruption by small additive noise.

Cited in

(1)

• The sampling complexity on nonconvex sparse phase retrieval problem

This page was built for publication: Sample-Efficient Low Rank Phase Retrieval

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5032652)