Robust Sensing of Low-Rank Matrices with Non-Orthogonal Sparse Decomposition
Author:
Preprint
Abstract
We consider the problem of recovering an unknown low-rank matrix X with (possibly) non-orthogonal, effectively sparse rank-1 decomposition from measurements y gathered in a linear measurement process A. We propose a variational formulation that lends itself to alternating minimization and whose global minimizers provably approximate X up to noise level. Working with a variant of robust injectivity, we derive reconstruction guarantees for various choices of A including sub-gaussian, Gaussian rank-1, and heavy-tailed measurements. Numerical experiments support the validity of our theoretical considerations.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Riemannian thresholding methods for row-sparse and low-rank matrix recoveryNumerical Algorithms, 2022
- Robust recovery of low-rank matrices with non-orthogonal sparse decomposition from incomplete measurementsApplied Mathematics and Computation, 2021
- NP-hardness and inapproximability of sparse PCAInformation Processing Letters, 2017
- Low rank matrix recovery from rank one measurementsApplied and Computational Harmonic Analysis, 2017
- Conditions on optimal support recovery in unmixing problems by means of multi-penalty regularizationInverse Problems, 2016
- Near-optimal estimation of simultaneously sparse and low-rank matrices from nested linear measurementsInformation and Inference: A Journal of the IMA, 2016
- Minimization of multi-penalty functionals by alternating iterative thresholding and optimal parameter choicesInverse Problems, 2014
- The intrinsic memorability of face photographs.Journal of Experimental Psychology: General, 2013
- One‐Bit Compressed Sensing by Linear ProgrammingCommunications on Pure and Applied Mathematics, 2013
- Iterative hard thresholding for compressed sensingApplied and Computational Harmonic Analysis, 2009