Adaptive robust estimation in sparse vector model

DOI10.1214/20-AOS2002zbMATH Open1476.62063arXiv1802.04230OpenAlexW3135175840MaRDI QIDQ820801FDOQ820801

Authors: Laetitia Comminges, Olivier Collier, Mohamed Ndaoud, Alexandre B. Tsybakov 

Publication date: 28 September 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: For the sparse vector model, we consider estimation of the target vector, of its L2-norm and of the noise variance. We construct adaptive estimators and establish the optimal rates of adaptive estimation when adaptation is considered with respect to the triplet "noise level - noise distribution - sparsity". We consider classes of noise distributions with polynomially and exponentially decreasing tails as well as the case of Gaussian noise. The obtained rates turn out to be different from the minimax non-adaptive rates when the triplet is known. A crucial issue is the ignorance of the noise variance. Moreover, knowing or not knowing the noise distribution can also influence the rate. For example, the rates of estimation of the noise variance can differ depending on whether the noise is Gaussian or sub-Gaussian without a precise knowledge of the distribution. Estimation of noise variance in our setting can be viewed as an adaptive variant of robust estimation of scale in the contamination model, where instead of fixing the "nominal" distribution in advance, we assume that it belongs to some class of distributions.

Full work available at URL: https://arxiv.org/abs/1802.04230

Recommendations

• Adaptive estimation of the sparsity in the Gaussian vector model
• Adaptive sparse regression
• Adaptive Lasso for vector multiplicative error models
• Robust estimation of sparse precision matrix using adaptive weighted graphical lasso approach
• Robust and sparse estimators for linear regression models
• Robust adaptive Lasso for variable selection
• The adaptive Lasso in high-dimensional sparse heteroscedastic models
• Adaptive estimation in two-way sparse reduced-rank regression
• Optimal adaptive estimation of linear functionals under sparsity
• Adaptive Lasso for sparse high-dimensional regression models

zbMATH Keywords

variance estimationrobust estimationadaptive estimationfunctional estimationminimax ratesparse vector model

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric robustness (62G35) Linear regression; mixed models (62J05) Minimax procedures in statistical decision theory (62C20) Functional data analysis (62R10)

Cites Work

• EigenPrism: inference for high dimensional signal-to-noise ratios
• Adaptive estimation of high-dimensional signal-to-noise ratios
• Optimal Estimation of Genetic Relatedness in High-Dimensional Linear Models
• Robust Statistics
• Scaled sparse linear regression
• Introduction to nonparametric estimation
• Title not available (Why is that?)
• Minimax estimation of linear and quadratic functionals on sparsity classes
• Title not available (Why is that?)
• Title not available (Why is that?)
• Minimax risks for sparse regressions: ultra-high dimensional phenomenons
• Optimal rates of convergence for estimating the null density and proportion of nonnull effects in large-scale multiple testing
• Pivotal estimation via square-root lasso in nonparametric regression
• Pivotal Estimation in High-Dimensional Regression via Linear Programming
• Minimax estimation of the noise level and of the deconvolution density in a semiparametric convolution model
• Sparse covariance matrix estimation in high-dimensional deconvolution
• Robust covariance and scatter matrix estimation under Huber's contamination model
• Adaptive estimation of the sparsity in the Gaussian vector model
• Slope meets Lasso: improved oracle bounds and optimality
• Optimal adaptive estimation of linear functionals under sparsity
• Minimax rate of testing in sparse linear regression
• Noise level estimation in high-dimensional linear models

Cited In (7)

• Adaptive estimation of high-dimensional signal-to-noise ratios
• Robust and tuning-free sparse linear regression via square-root slope
• Minimax estimation of linear and quadratic functionals on sparsity classes
• All-in-one robust estimator of the Gaussian mean
• On estimation of nonsmooth functionals of sparse normal means
• Estimation of the \(\ell_2\)-norm and testing in sparse linear regression with unknown variance
• Adaptive estimation of the sparsity in the Gaussian vector model

Uses Software

• EigenPrism

This page was built for publication: Adaptive robust estimation in sparse vector model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q820801)