Nonconvex Robust Low-rank Matrix Recovery

TL;DR

This paper introduces a nonconvex, robust approach for low-rank matrix recovery from corrupted measurements, proving exact recovery under certain conditions and demonstrating efficient convergence of a subgradient method.

Contribution

It presents a novel nonconvex formulation with theoretical guarantees for exact recovery despite high corruption levels, and analyzes the convergence of a subgradient method.

Findings

Exact recovery is possible with up to nearly 50% corrupted measurements.

The optimization landscape is sharp and weakly convex, enabling linear convergence.

Numerical experiments confirm the effectiveness of the proposed method.

Abstract

In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values. We consider a nonsmooth nonconvex formulation of the problem, in which we explicitly enforce the low-rank property of the solution by using a factored representation of the matrix variable and employ an $\ell_1$-loss function to robustify the solution against outliers. We show that even when a constant fraction (which can be up to almost half) of the measurements are arbitrarily corrupted, as long as certain measurement operators arising from the measurement model satisfy the so-called $\ell_1/\ell_2$-restricted isometry property, the ground-truth matrix can be exactly recovered from any global minimum of the resulting optimization problem. Furthermore, we show that the objective function of the optimization problem is sharp and weakly convex. Consequently, a subgradient Method (SubGM) with geometrically diminishing step sizes will converge linearly to the ground-truth matrix when suitably initialized. We demonstrate the efficacy of the SubGM for the nonconvex robust low-rank matrix recovery problem with various numerical experiments.