Sample efficient inductive matrix completion with noise and inexact side information

TL;DR

This paper introduces a nonconvex gradient descent method for noisy inductive matrix completion that achieves near-optimal sample complexity by leveraging side information, with proven convergence and error bounds.

Contribution

It establishes a regularity condition for the IMC loss function at reduced sample complexity and extends the analysis to inexact side information, closing prior gaps.

Findings

Achieves linear convergence with sample complexity depending on effective problem size

Estimation error scales with side information quality, not ambient dimension

Validates theoretical results with simulations and MovieLens experiments

Abstract

Low-rank matrix completion is a widely studied problem with many variants. Inductive matrix completion (IMC) incorporates row and column side information to significantly narrow the search space. Prior work falls into two regimes: methods that exploit this structure to achieve reduced sample complexity but only in noiseless settings, and methods that handle noise but require sample complexity matching the ambient matrix dimension, forfeiting the sample efficiency that side information should provide. In this paper, we close this gap by studying noisy IMC with a nonconvex projected gradient descent algorithm with spectral initialization. Our main technical contribution is establishing a regularity condition for the IMC loss function that holds at the reduced sample complexity determined by the effective problem size, scaling with the side information dimension a rather than the ambient dimension n. This directly yields linear convergence and an estimation error that both depend only on the effective problem size rather than the ambient matrix dimension. We further extend our analysis to the inexact side information setting, demonstrating that the reduced sample complexity is maintained and the estimation error is order-optimal with respect to the inexactness of the side information. Extensive simulations and real-world experiments on the MovieLens dataset validate our theoretical findings.