Pivotal Estimation in High-Dimensional Regression via Linear Programming

DOI10.1007/978-3-642-41136-6_17zbMATH Open1325.62088arXiv1303.7092OpenAlexW2147152516MaRDI QIDQ5264101FDOQ5264101

Authors: Eric Gautier, Alexandre B. Tsybakov 

Publication date: 20 July 2015

Published in: Empirical Inference (Search for Journal in Brave)

Abstract: We propose a new method of estimation in high-dimensional linear regression model. It allows for very weak distributional assumptions including heteroscedasticity, and does not require the knowledge of the variance of random errors. The method is based on linear programming only, so that its numerical implementation is faster than for previously known techniques using conic programs, and it allows one to deal with higher dimensional models. We provide upper bounds for estimation and prediction errors of the proposed estimator showing that it achieves the same rate as in the more restrictive situation of fixed design and i.i.d. Gaussian errors with known variance. Following Gautier and Tsybakov (2011), we obtain the results under weaker sensitivity assumptions than the restricted eigenvalue or assimilated conditions.

Full work available at URL: https://arxiv.org/abs/1303.7092

Recommendations

• \(p\)-values for high-dimensional regression
• Linear and conic programming estimators in high dimensional errors-in-variables models
• Partial least squares prediction in high-dimensional regression
• Estimation of linear projections of non-sparse coefficients in high-dimensional regression
• Estimation in high-dimensional analysis and multivariate linear models
• High dimensional inverse covariance matrix estimation via linear programming
• Pivotal estimation via square-root lasso in nonparametric regression
• M-estimation in high-dimensional linear model
• Penalized least-squares estimation for regression coefficients in high-dimensional partially linear models
• Empirical likelihood for high-dimensional linear regression models

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Linear programming (90C05)

Cited In (6)

• Adaptive robust estimation in sparse vector model
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• An \(\{\ell_{1},\ell_{2},\ell_{\infty}\}\)-regularization approach to high-dimensional errors-in-variables models
• Linear Hypothesis Testing in Dense High-Dimensional Linear Models
• High-dimensional linear models with many endogenous variables
• Significance testing in non-sparse high-dimensional linear models

This page was built for publication: Pivotal Estimation in High-Dimensional Regression via Linear Programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5264101)