Robust Sensing of Low-Rank Matrices with Non-Orthogonal Sparse Decomposition

03/09/2021
by   Johannes Maly, et al.
0

We consider the problem of recovering an unknown low-rank matrix X with (possibly) non-orthogonal, effectively sparse rank-1 decomposition from incomplete and inaccurate 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 from y 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.

READ FULL TEXT
research
09/24/2018

Nonconvex Robust Low-rank Matrix Recovery

In this paper we study the problem of recovering a low-rank matrix from ...
research
03/06/2020

An analysis of noise folding for low-rank matrix recovery

Previous work regarding low-rank matrix recovery has concentrated on the...
research
03/13/2023

An Improved Sample Complexity for Rank-1 Matrix Sensing

Matrix sensing is a problem in signal processing and machine learning th...
research
09/23/2020

Learning Mixtures of Low-Rank Models

We study the problem of learning mixtures of low-rank models, i.e. recon...
research
02/25/2023

Inaccurate Label Distribution Learning

Label distribution learning (LDL) trains a model to predict the relevanc...
research
05/27/2020

Simultaneous Diagonalization of Incomplete Matrices and Applications

We consider the problem of recovering the entries of diagonal matrices {...
research
10/13/2021

The springback penalty for robust signal recovery

We propose a new penalty, named as the springback penalty, for construct...

Please sign up or login with your details

Forgot password? Click here to reset