Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation
نویسندگان
چکیده
We present a unified framework for low-rank matrix estimation with nonconvex penalty. A proximal gradient homotopy algorithm is developed to solve the proposed optimization problem. Theoretically, we first prove that the proposed estimator attains a faster statistical rate than the traditional low-rank matrix estimator with nuclear norm penalty. Moreover, we rigorously show that under a certain condition on the magnitude of the nonzero singular values, the proposed estimator enjoys oracle property (i.e., exactly recovers the true rank of the matrix), besides attaining a faster rate. Extensive numerical experiments on both synthetic and real world datasets corroborate our theoretical findings.
منابع مشابه
PAGE: Robust Pattern Guided Estimation of Large Covariance Matrix
We study the problem of estimating large covariance matrices under two types of structural assumptions: (i) The covariance matrix is the summation of a low rank matrix and a sparse matrix, and we have some prior information on the sparsity pattern of the sparse matrix; (ii) The data follow a transelliptical distribution. The former structure regulates the parameter space and has its roots in di...
متن کاملA Nonconvex Optimization Framework for Low Rank Matrix Estimation
We study the estimation of low rank matrices via nonconvex optimization. Compared with convex relaxation, nonconvex optimization exhibits superior empirical performance for large scale instances of low rank matrix estimation. However, the understanding of its theoretical guarantees are limited. In this paper, we define the notion of projected oracle divergence based on which we establish suffic...
متن کاملTight oracle bounds for low-rank matrix recovery from a minimal number of random measurements
This paper presents several novel theoretical results regarding the recovery of a low-rank matrix from just a few measurements consisting of linear combinations of the matrix entries. We show that properly constrained nuclear-normminimization stably recovers a low-rank matrix from a constant number of noisy measurements per degree of freedom; this seems to be the first result of this nature. Fu...
متن کاملNuclear Norm Penalization and Optimal Rates for Noisy Low-rank Matrix Completion
This paper deals with the trace regression model where n entries or linear combinations of entries of an unknown m1 × m2 matrix A0 corrupted by noise are observed. We propose a new nuclear norm penalized estimator of A0 and establish a general sharp oracle inequality for this estimator for arbitrary values of n,m1,m2 under the condition of isometry in expectation. Then this method is applied to...
متن کاملRegularized Rank - Based Estimation of High - Dimensional Nonparanormal Graphical Models
A sparse precision matrix can be directly translated into a sparse Gaussian graphical model under the assumption that the data follow a joint normal distribution. This neat property makes high-dimensional precision matrix estimation very appealing in many applications. However, in practice we often face nonnormal data, and variable transformation is often used to achieve normality. In this pape...
متن کامل