Weakly decomposable regularization penalties and structured sparsity

DOI10.1111/SJOS.12032MaRDI QIDQ5413946zbMATH OpenOpenAlexFDO

Authors Sara Van De Geer

Publication date 2 May 2014

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1204.4813

zbMATH Keywords

Lassoregularizationsharp oracle inequalitysparsityweakly decomposable norm

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: It has been shown in literature that the Lasso estimator, or l1-penalized least squares estimator, enjoys good oracle properties. This paper examines which special properties of the l1-penalty allow for sharp oracle results, and then extends the situation to general norm-based penalties that satisfy a weak decomposability condition.

Recommendations

• Regularizers for structured sparsity
• A note on ``Reguralizers for structured sparsity
• Structured sparsity through convex optimization
• Sparse Approximation via Penalty Decomposition Methods
• Structured sparsity via alternating direction methods
• Sparse Regularization via Convex Analysis
• Sparse regularization with l ^q penalty term
• Structured sparsity: discrete and convex approaches
• Weakly Convex Regularized Robust Sparse Recovery Methods With Theoretical Guarantees

Cited in

(19)

• Regularization and the small-ball method. I: Sparse recovery
• Sampling from non-smooth distributions through Langevin diffusion
• Asymptotic linear expansion of regularized M-estimators
• Penalized wavelet estimation and robust denoising for irregular spaced data
• Robust machine learning by median-of-means: theory and practice
• Asymptotic properties of concave \(L_1\)-norm group penalties
• Sharp oracle inequalities for low-complexity priors
• On model selection consistency of regularized M-estimators
• Worst possible sub-directions in high-dimensional models
• Weak convergence of the regularization path in penalized M-estimation
• Oracle inequalities for local and global empirical risk minimizers
• Sharp oracle inequalities for square root regularization
• Group regularized estimation under structural hierarchy
• scientific article; zbMATH DE number 7306909 (Why is no real title available?)
• Sparse recovery under weak moment assumptions
• Generalized linear models with structured sparsity estimators
• Sparse principal component analysis for high‐dimensional stationary time series
• Lasso in Infinite dimension: application to variable selection in functional multivariate linear regression
• Hierarchical Bayesian inverse problems: a high-dimensional statistics viewpoint

Describes a project that uses

Uses Software

• hgam

This page was built for publication: Weakly decomposable regularization penalties and structured sparsity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5413946)