Robust Low-Rank Matrix Estimation

TL;DR

This paper introduces robust nuclear norm penalized estimators for matrix completion using absolute value and Huber loss functions, providing theoretical guarantees and demonstrating their effectiveness through simulations.

Contribution

It develops and analyzes robust low-rank matrix estimators with theoretical error bounds under high-dimensional settings, extending previous work to more robust loss functions.

Findings

Sharp oracle inequalities established for robust estimators.

Error bounds hold under weak sparsity conditions.

Simulations confirm theoretical predictions.

Abstract

Many results have been proved for various nuclear norm penalized estimators of the uniform sampling matrix completion problem. However, most of these estimators are not robust: in most of the cases the quadratic loss function and its modifications are used. We consider robust nuclear norm penalized estimators using two well-known robust loss functions: the absolute value loss and the Huber loss. Under several conditions on the sparsity of the problem (i.e. the rank of the parameter matrix) and on the regularity of the risk function sharp and non-sharp oracle inequalities for these estimators are shown to hold with high probability. As a consequence, the asymptotic behavior of the estimators is derived. Similar error bounds are obtained under the assumption of weak sparsity, i.e. the case where the matrix is assumed to be only approximately low-rank. In all our results we consider a high-dimensional setting. In this case, this means that we assume $n\leq pq$. Finally, various simulations confirm our theoretical results.