Weighted Matrix Completion and Recovery with Prior Subspace Information

TL;DR

This paper introduces a weighted nuclear norm approach for matrix completion that leverages prior subspace information, reducing sample complexity and improving recovery performance.

Contribution

It provides a theoretical framework quantifying how prior subspace knowledge enhances matrix completion and recovery, with significant practical implications.

Findings

Prior knowledge reduces sample complexity logarithmically.

Weighted nuclear norm improves recovery accuracy.

Numerical simulations show magnified benefits.

Abstract

An incoherent low-rank matrix can be efficiently reconstructed after observing a few of its entries at random, and then solving a convex program that minimizes the nuclear norm. In many applications, in addition to these entries, potentially valuable prior knowledge about the column and row spaces of the matrix is also available to the practitioner. In this paper, we incorporate this prior knowledge in matrix completion---by minimizing a weighted nuclear norm---and precisely quantify any improvements. In particular, we find in theory that reliable prior knowledge reduces the sample complexity of matrix completion by a logarithmic factor, and the observed improvement in numerical simulations is considerably more magnified. We also present similar results for the closely related problem of matrix recovery from generic linear measurements.