A Rank-Corrected Procedure for Matrix Completion with Fixed Basis Coefficients

by   Weimin Miao, et al.

For the problems of low-rank matrix completion, the efficiency of the widely-used nuclear norm technique may be challenged under many circumstances, especially when certain basis coefficients are fixed, for example, the low-rank correlation matrix completion in various fields such as the financial market and the low-rank density matrix completion from the quantum state tomography. To seek a solution of high recovery quality beyond the reach of the nuclear norm, in this paper, we propose a rank-corrected procedure using a nuclear semi-norm to generate a new estimator. For this new estimator, we establish a non-asymptotic recovery error bound. More importantly, we quantify the reduction of the recovery error bound for this rank-corrected procedure. Compared with the one obtained for the nuclear norm penalized least squares estimator, this reduction can be substantial (around 50 necessary and sufficient conditions for rank consistency in the sense of Bach (2008). Very interestingly, these conditions are highly related to the concept of constraint nondegeneracy in matrix optimization. As a byproduct, our results provide a theoretical foundation for the majorized penalty method of Gao and Sun (2010) and Gao (2010) for structured low-rank matrix optimization problems. Extensive numerical experiments demonstrate that our proposed rank-corrected procedure can simultaneously achieve a high recovery accuracy and capture the low-rank structure.


page 1

page 2

page 3

page 4


Analysis of Nuclear Norm Regularization for Full-rank Matrix Completion

In this paper, we provide a theoretical analysis of the nuclear-norm reg...

Approximately low-rank recovery from noisy and local measurements by convex program

Low-rank matrix models have been universally useful for numerous applica...

On Inferences from Completed Data

Matrix completion has become an extremely important technique as data sc...

Max-Norm Optimization for Robust Matrix Recovery

This paper studies the matrix completion problem under arbitrary samplin...

Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas

We study the adaptive estimation of copula correlation matrix Σ for the ...

Top-N Recommender System via Matrix Completion

Top-N recommender systems have been investigated widely both in industry...

Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization

We describe novel subgradient methods for a broad class of matrix optimi...

Please sign up or login with your details

Forgot password? Click here to reset