GNMR: A provable one-line algorithm for low rank matrix recovery

06/24/2021
by   Pini Zilber, et al.
0

Low rank matrix recovery problems, including matrix completion and matrix sensing, appear in a broad range of applications. In this work we present GNMR – an extremely simple iterative algorithm for low rank matrix recovery, based on a Gauss-Newton linearization. On the theoretical front, we derive recovery guarantees for GNMR in both the matrix sensing and matrix completion settings. A key property of GNMR is that it implicitly keeps the factor matrices approximately balanced throughout its iterations. On the empirical front, we show that for matrix completion with uniform sampling, GNMR performs better than several popular methods, especially when given very few observations close to the information limit.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/11/2018

Exploiting the structure effectively and efficiently in low rank matrix recovery

Low rank model arises from a wide range of applications, including machi...
research
10/25/2020

Adversarial Robust Low Rank Matrix Estimation: Compressed Sensing and Matrix Completion

We consider robust low rank matrix estimation when random noise is heavy...
research
04/27/2023

A Majorization-Minimization Gauss-Newton Method for 1-Bit Matrix Completion

In 1-bit matrix completion, the aim is to estimate an underlying low-ran...
research
09/13/2018

Clipped Matrix Completion: a Remedy for Ceiling Effects

We consider the recovery of a low-rank matrix from its clipped observati...
research
04/08/2015

Structured Matrix Completion with Applications to Genomic Data Integration

Matrix completion has attracted significant recent attention in many fie...
research
12/14/2018

Low-rank Matrix Completion in a General Non-orthogonal Basis

This paper considers theoretical analysis of recovering a low rank matri...
research
02/25/2011

Sparse Bayesian Methods for Low-Rank Matrix Estimation

Recovery of low-rank matrices has recently seen significant activity in ...

Please sign up or login with your details

Forgot password? Click here to reset