On the prediction loss of the Lasso in the partially labeled setting

DOI10.1214/18-EJS1457zbMath1408.62114arXiv1606.06179WikidataQ129087191 ScholiaQ129087191MaRDI QIDQ1616320

Arnak S. Dalalyan, Quentin Paris, Edwin Grappin, Pierre C. Bellec

Publication date: 1 November 2018

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1606.06179

zbMATH Keywords

sparsityhigh-dimensional regressionoracle inequalityLassotransductive learningsemi-supervised learningprediction risk

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (7)

A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery ⋮ Semi-supervised empirical risk minimization: using unlabeled data to improve prediction ⋮ Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood ⋮ Oracle inequalities for high-dimensional prediction ⋮ Rough set-based feature selection for weakly labeled data ⋮ Minimax semi-supervised set-valued approach to multi-class classification ⋮ Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Solution of linear ill-posed problems using overcomplete dictionaries
• The lower tail of random quadratic forms with applications to ordinary least squares
• Transductive versions of the Lasso and the Dantzig selector
• On the prediction performance of the Lasso
• Statistics for high-dimensional data. Methods, theory and applications.
• Exponential screening and optimal rates of sparse estimation
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• User-friendly tail bounds for sums of random matrices
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Regularization and the small-ball method. I: Sparse recovery
• On the conditions used to prove oracle results for the Lasso
• Slope meets Lasso: improved oracle bounds and optimality
• Pivotal estimation via square-root lasso in nonparametric regression
• Simultaneous analysis of Lasso and Dantzig selector
• Bounds of restricted isometry constants in extreme asymptotics: formulae for Gaussian matrices
• Reconstruction From Anisotropic Random Measurements
• Scaled sparse linear regression
• Accuracy Guarantees for <formula formulatype="inline"> <tex Notation="TeX">$\ell_1$</tex></formula>-Recovery
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Sparse estimation by exponential weighting

This page was built for publication: On the prediction loss of the Lasso in the partially labeled setting