Robust recovery of low-rank matrices and low-tubal-rank tensors from noisy sketches

06/02/2022
by   Anna Ma, et al.
0

A common approach for compressing large-scale data is through matrix sketching. In this work, we consider the problem of recovering low-rank matrices from two noisy sketches using the double sketching algorithm discussed in Fazel et al. (2008). Using tools from non-asymptotic random matrix theory, we provide the first theoretical guarantees characterizing the error between the output of the double sketch algorithm and the ground truth low-rank matrix. We apply our result to the problems of low-rank matrix approximation and low-tubal-rank tensor recovery.

READ FULL TEXT

page 11

page 12

research
05/21/2017

Improved Algorithms for Matrix Recovery from Rank-One Projections

We consider the problem of estimation of a low-rank matrix from a limite...
research
12/05/2014

Two step recovery of jointly sparse and low-rank matrices: theoretical guarantees

We introduce a two step algorithm with theoretical guarantees to recover...
research
06/14/2020

Nonasymptotic Guarantees for Low-Rank Matrix Recovery with Generative Priors

Many problems in statistics and machine learning require the reconstruct...
research
05/12/2022

Sketching sparse low-rank matrices with near-optimal sample- and time-complexity

We consider the problem of recovering an n_1 × n_2 low-rank matrix with ...
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
05/28/2019

Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix

This paper studies how to sketch element-wise functions of low-rank matr...
research
05/16/2023

Parameter optimization for low-rank matrix recovery in hyperspectral imaging

An approach to parameter optimization for the low-rank matrix recovery m...

Please sign up or login with your details

Forgot password? Click here to reset