Matrix Completion via Max-Norm Constrained Optimization

TL;DR

This paper introduces a max-norm constrained approach for noisy matrix completion that is robust under general sampling schemes, providing optimal convergence rates and practical algorithms.

Contribution

It proposes a novel max-norm constrained empirical risk minimization method that is minimax rate-optimal for matrix completion under non-uniform sampling.

Findings

Achieves optimal convergence rates under general sampling.

Provides a unified guarantee for approximate recovery.

Discusses efficient algorithms for max-norm regularized optimization.

Abstract

Matrix completion has been well studied under the uniform sampling model and the trace-norm regularized methods perform well both theoretically and numerically in such a setting. However, the uniform sampling model is unrealistic for a range of applications and the standard trace-norm relaxation can behave very poorly when the underlying sampling scheme is non-uniform. In this paper we propose and analyze a max-norm constrained empirical risk minimization method for noisy matrix completion under a general sampling model. The optimal rate of convergence is established under the Frobenius norm loss in the context of approximately low-rank matrix reconstruction. It is shown that the max-norm constrained method is minimax rate-optimal and yields a unified and robust approximate recovery guarantee, with respect to the sampling distributions. The computational effectiveness of this method is also discussed, based on first-order algorithms for solving convex optimizations involving max-norm regularization.