Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block \ell _{1}/\ell _{\infty} -Regularization

DOI10.1109/TIT.2011.2144150zbMATH Open1365.62274OpenAlexW1480312878MaRDI QIDQ5273638FDOQ5273638

Authors Sahand Negahban, Martin J. Wainwright

Publication date 12 July 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.2011.2144150

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Quadratic programming (90C20) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cited in

(15)

• Discrete optimization methods for group model selection in compressed sensing
• Variable selection and collinearity processing for multivariate data via row-elastic-net regularization
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
• Convex support vector regression
• \(L_1\)-regularized least squares for support recovery of high dimensional single index models with Gaussian designs
• Detecting clusters in multivariate response regression
• Structured sparsity through convex optimization
• Non-convex penalized multitask regression using data depth-based penalties
• Structured estimation for the nonparametric Cox model
• Block-diagonal precision matrix regularization for ultra-high dimensional data
• Modeling association between multivariate correlated outcomes and high-dimensional sparse covariates: the adaptive SVS method
• Low complexity regularization of linear inverse problems
• On Degrees of Freedom of Projection Estimators With Applications to Multivariate Nonparametric Regression
• On group-wise \(\ell_p\) regularization: theory and efficient algorithms
• A no-free-lunch theorem for multitask learning

This page was built for publication: Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block $\ell _{1}/\ell _{\infty} $-Regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5273638)