Optimal tuning-free convex relaxation for noisy matrix completion

Abstract

This paper is concerned with noisy matrix completion--the problem of recovering a low-rank matrix from partial and noisy entries. Under uniform sampling and incoherence assumptions, we prove that a tuning-free square-root matrix completion estimator (square-root MC) achieves optimal statistical performance for solving the noisy matrix completion problem. Similar to the square-root Lasso estimator in high-dimensional linear regression, square-root MC does not rely on the knowledge of the size of the noise. While solving square-root MC is a convex program, our statistical analysis of square-root MC hinges on its intimate connections to a nonconvex rank-constrained estimator.

Accepted to IEEE Transactions on Information Theory

References in corpus (5)

• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Spectral Methods for Data Science: A Statistical Perspective
• Inference for Heteroskedastic PCA with Missing Data
• Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
• Robust Matrix Completion with Heavy-tailed Noise