Iterative Hard Thresholding for Low-Rank Recovery from Rank-One Projections
Numerical Analysis
2018-10-30 v1
Abstract
A novel algorithm for the recovery of low-rank matrices acquired via compressive linear measurements is proposed and analyzed. The algorithm, a variation on the iterative hard thresholding algorithm for low-rank recovery, is designed to succeed in situations where the standard rank-restricted isometry property fails, e.g. in case of subexponential unstructured measurements or of subgaussian rank-one measurements. The stability and robustness of the algorithm are established based on distinctive matrix-analytic ingredients and its performance is substantiated numerically.
Keywords
Cite
@article{arxiv.1810.11749,
title = {Iterative Hard Thresholding for Low-Rank Recovery from Rank-One Projections},
author = {Simon Foucart and Srinivas Subramanian},
journal= {arXiv preprint arXiv:1810.11749},
year = {2018}
}