Slope meets Lasso: improved oracle bounds and optimality

DOI10.1214/17-AOS1670zbMath1405.62056arXiv1605.08651OpenAlexW2962710557WikidataQ105584294 ScholiaQ105584294MaRDI QIDQ1990596

Alexandre B. Tsybakov, Guillaume Lecué, Pierre C. Bellec

Publication date: 25 October 2018

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

Full work available at URL: https://arxiv.org/abs/1605.08651

zbMATH Keywords

high-dimensional statistics Lasso sparse linear regression minimax rates slope

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Estimation in multivariate analysis (62H12) Linear regression; mixed models (62J05) Nonparametric estimation (62G05) Minimax procedures in statistical decision theory (62C20)

Related Items

Fundamental barriers to high-dimensional regression with convex penalties, Canonical thresholding for nonsparse high-dimensional linear regression, Adaptive robust estimation in sparse vector model, An efficient semismooth Newton method for adaptive sparse signal recovery problems, On the prediction loss of the Lasso in the partially labeled setting, Iterative algorithm for discrete structure recovery, Penalized least square in sparse setting with convex penalty and non Gaussian errors, Sparse index clones via the sorted ℓ₁-Norm, Adaptive Bayesian SLOPE: Model Selection With Incomplete Data, On Kendall's regression, Sample average approximation with heavier tails II: localization in stochastic convex optimization and persistence results for the Lasso, Characterizing the SLOPE trade-off: a variational perspective and the Donoho-Tanner limit, Estimation of the \(\ell_2\)-norm and testing in sparse linear regression with unknown variance, Sparse optimization via vector \(k\)-norm and DC programming with an application to feature selection for support vector machines, Regularization, sparse recovery, and median-of-means tournaments, Debiased lasso for generalized linear models with a diverging number of covariates, Debiasing convex regularized estimators and interval estimation in linear models, Lasso in Infinite dimension: application to variable selection in functional multivariate linear regression, Robust machine learning by median-of-means: theory and practice, Retire: robust expectile regression in high dimensions, On Lasso and Slope drift estimators for Lévy-driven Ornstein-Uhlenbeck processes, The Lasso with general Gaussian designs with applications to hypothesis testing, An alternative to synthetic control for models with many covariates under sparsity, On the asymptotic properties of SLOPE, Structural inference in sparse high-dimensional vector autoregressions, ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels, Adaptive Huber Regression, Oracle inequalities for high-dimensional prediction, Improved bounds for square-root Lasso and square-root slope, Sharp oracle inequalities for least squares estimators in shape restricted regression, Facilitating OWL norm minimizations, Sparse inference of the drift of a high-dimensional Ornstein-Uhlenbeck process, Sorted concave penalized regression, Degrees of freedom in submodular regularization: a computational perspective of Stein's unbiased risk estimate, A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning, Iteratively reweighted \(\ell_1\)-penalized robust regression, On the sparsity of Mallows model averaging estimator, Second-order Stein: SURE for SURE and other applications in high-dimensional inference, Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions, Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation, Unnamed Item, Unnamed Item, Unnamed Item, Nonregular and minimax estimation of individualized thresholds in high dimension with binary responses, A Unifying Tutorial on Approximate Message Passing

Cites Work