Matrix rigidity and the ill-posedness of Robust PCA and matrix completion

11/14/2018
by   Jared Tanner, et al.
0

Robust Principal Component Analysis (PCA) (Candes et al., 2011) and low-rank matrix completion (Recht et al., 2010) are extensions of PCA to allow for outliers and missing entries respectively. It is well-known that solving these problems requires a low coherence between the low-rank matrix and the canonical basis, since in the extreme cases -- when the low-rank matrix we wish to recover is also sparse -- there is an inherent ambiguity. However, the well-posedness issue in both problems is an even more fundamental one: in some cases, both Robust PCA and matrix completion can fail to have any solutions at due to the set of low-rank plus sparse matrices not being closed, which in turn is equivalent to the notion of the matrix rigidity function not being lower semicontinuous (Kumar et al., 2014). By constructing infinite families of matrices, we derive bounds on the rank and sparsity such that the set of low-rank plus sparse matrices is not closed. We also demonstrate numerically that a wide range of non-convex algorithms for both Robust PCA and matrix completion have diverging components when applied to our constructed matrices. An analogy can be drawn to the case of sets of higher order tensors not being closed under canonical polyadic (CP) tensor rank, rendering the best low-rank tensor approximation unsolvable (Silva and Lim, 2008) and hence encourage the use of multilinear tensor rank (De Lathauwer, 2000).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2021

Provable Low Rank Plus Sparse Matrix Separation Via Nonconvex Regularizers

This paper considers a large class of problems where we seek to recover ...
research
10/01/2014

Generalized Low Rank Models

Principal components analysis (PCA) is a well-known technique for approx...
research
01/15/2021

Local Search Algorithms for Rank-Constrained Convex Optimization

We propose greedy and local search algorithms for rank-constrained conve...
research
12/07/2015

Pseudo-Bayesian Robust PCA: Algorithms and Analyses

Commonly used in computer vision and other applications, robust PCA repr...
research
04/22/2019

Low-Rank Approximation from Communication Complexity

In low-rank approximation with missing entries, given A∈R^n× n and binar...
research
03/11/2015

Online Matrix Completion and Online Robust PCA

This work studies two interrelated problems - online robust PCA (RPCA) a...
research
05/27/2019

Tuning Free Rank-Sparse Bayesian Matrix and Tensor Completion with Global-Local Priors

Matrix and tensor completion are frameworks for a wide range of problems...

Please sign up or login with your details

Forgot password? Click here to reset