High dimensional matrix estimation with unknown variance of the noise

DOI10.5705/SS.2013.167MaRDI QIDQ2960507zbMATH OpenOpenAlexFDO

Authors Stéphane Gaïffas, Olga Klopp

Publication date 17 February 2017

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1112.3055

zbMATH Keywords

low rank matrix estimationmatrix completionmatrix regressionunknown variance of the noise

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Estimation in multivariate analysis (62H12)

Abstract: We propose a new pivotal method for estimating high-dimensional matrices. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix $A_0$ corrupted by noise. We propose a new method for estimating $A_0$ which does not rely on the knowledge or an estimation of the standard deviation of the noise $sigma$. Our estimator achieves, up to a logarithmic factor, optimal rates of convergence under the Frobenius risk and, thus, has the same prediction performance as previously proposed estimators which rely on the knowledge of $sigma$. Our method is based on the solution of a convex optimization problem which makes it computationally attractive.

Recommendations

• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Estimation of high-dimensional low-rank matrices
• On estimation of the noise variance in high dimensional probabilistic principal component analysis
• High-dimensional covariance matrix estimation. An introduction to random matrix theory
• Robust estimation of high-dimensional covariance and precision matrices
• scientific article; zbMATH DE number 5204610
• High-dimensional covariance estimation
• High-dimensional regression with unknown variance
• A unified approach to estimating a normal mean matrix in high and low dimensions
• On estimation of a matrix of normal means with unknown covariance matrix

Cited in

(12)

• Algorithms for matrix estimation
• A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
• On the robustness of noise-blind low-rank recovery from rank-one measurements
• Noise level estimation in high-dimensional linear models
• A fast algorithm for the semi-definite relaxation of the state estimation problem in power grids
• On matrix estimation under monotonicity constraints
• Design-free estimation of variance matrices
• Reconstruction of a low-rank matrix in the presence of Gaussian noise
• Bayesian singular value regularization via a cumulative shrinkage process
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Improved matrix uncertainty selector
• Matrix denoising with partial noise statistics: optimal singular value shrinkage of spiked F-matrices

This page was built for publication: High dimensional matrix estimation with unknown variance of the noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2960507)