Oracle inequalities and optimal inference under group sparsity

DOI10.1214/11-AOS896zbMath1306.62156arXiv1007.1771OpenAlexW3122814465MaRDI QIDQ651028

Massimiliano Pontil, Karim Lounici, Sara van de Geer, Alexandre B. Tsybakov

Publication date: 8 December 2011

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

Full work available at URL: https://arxiv.org/abs/1007.1771

zbMATH Keywords

minimax riskoracle inequalitiesgroup lassogroup sparsitystatistical learningpenalized least squaresmoment inequality

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Minimax procedures in statistical decision theory (62C20) Statistical ranking and selection procedures (62F07)

Related Items

Minimax estimation in multi-task regression under low-rank structures, Posterior contraction in group sparse logit models for categorical responses, Adaptive estimation in multivariate response regression with hidden variables, The benefit of group sparsity in group inference with de-biased scaled group Lasso, Solution of linear ill-posed problems using overcomplete dictionaries, Multivariate sparse group lasso for the multivariate multiple linear regression with an arbitrary group structure, Penalized least square in sparse setting with convex penalty and non Gaussian errors, Improved linear regression prediction by transfer learning, A varying-coefficient panel data model with fixed effects: theory and an application to US commercial banks, Robust grouped variable selection using distributionally robust optimization, Trace regression model with simultaneously low rank and row(column) sparse parameter, Structured variable selection via prior-induced hierarchical penalty functions, Joint rank and variable selection for parsimonious estimation in a high-dimensional finite mixture regression model, Variable selection and structure identification for varying coefficient Cox models, Monte Carlo Simulation for Lasso-Type Problems by Estimator Augmentation, Bayesian linear regression for multivariate responses under group sparsity, Grouping strategies and thresholding for high dimensional linear models, ``Grouping strategies and thresholding for high dimensional linear models: discussion, ``Grouping strategies and thresholding for high dimensional linear models: rejoinder, Quantile regression with group Lasso for classification, Variable selection, monotone likelihood ratio and group sparsity, Grouped variable selection with discrete optimization: computational and statistical perspectives, Adaptive bi-level variable selection for multivariate failure time model with a diverging number of covariates, Generalized linear models with structured sparsity estimators, Joint association and classification analysis of multi‐view data, Group sparse recovery via group square-root elastic net and the iterative multivariate thresholding-based algorithm, Variable selection in heterogeneous panel data models with cross‐sectional dependence, High-Dimensional Gaussian Graphical Regression Models with Covariates, Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model, A penalized two-pass regression to predict stock returns with time-varying risk premia, Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data, Unnamed Item, Lasso in Infinite dimension: application to variable selection in functional multivariate linear regression, Statistical and computational limits for sparse matrix detection, Multi-Task Learning with High-Dimensional Noisy Images, Adaptive and robust multi-task learning, Expectile trace regression via low-rank and group sparsity regularization, Regularizers for structured sparsity, A group adaptive elastic-net approach for variable selection in high-dimensional linear regression, Model selection in regression under structural constraints, Least squares after model selection in high-dimensional sparse models, Sparse PCA: optimal rates and adaptive estimation, A general framework for Bayes structured linear models, On the finite-sample analysis of \(\Theta\)-estimators, Estimation and variable selection with exponential weights, Sparse regression and support recovery with \(\mathbb{L}_2\)-boosting algorithms, Consistent group selection with Bayesian high dimensional modeling, On the finite-sample analysis of \(\Theta\)-estimators, Discrete optimization methods for group model selection in compressed sensing, Robust inference on average treatment effects with possibly more covariates than observations, Robust regression with compositional covariates, Unnamed Item, Decomposable norm minimization with proximal-gradient homotopy algorithm, Slope meets Lasso: improved oracle bounds and optimality, Pivotal estimation via square-root lasso in nonparametric regression, Estimation of high-dimensional low-rank matrices, Greedy variance estimation for the LASSO, Unnamed Item, Bayesian MIDAS penalized regressions: estimation, selection, and prediction, Prediction and estimation consistency of sparse multi-class penalized optimal scoring, Gelfand numbers related to structured sparsity and Besov space embeddings with small mixed smoothness, Simultaneous feature selection and clustering based on square root optimization, Group Regularized Estimation Under Structural Hierarchy, Adaptive estimation of the rank of the coefficient matrix in high-dimensional multivariate response regression models, Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach, Structured sparsity through convex optimization, A selective review of group selection in high-dimensional models, High-dimensional regression with unknown variance, A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers, Sparse estimation by exponential weighting, Randomized maximum-contrast selection: subagging for large-scale regression, Log-Contrast Regression with Functional Compositional Predictors: Linking Preterm Infant's Gut Microbiome Trajectories to Neurobehavioral Outcome, A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression, Tuning-Free Heterogeneity Pursuit in Massive Networks, Robust regression via mutivariate regression depth, Joint variable and rank selection for parsimonious estimation of high-dimensional matrices, Tight conditions for consistency of variable selection in the context of high dimensionality, Accuracy guaranties for \(\ell_{1}\) recovery of block-sparse signals, The de-biased group Lasso estimation for varying coefficient models, AIC for the group Lasso in generalized linear models, Sharp oracle inequalities for low-complexity priors, Oracle inequalities for weighted group Lasso in high-dimensional misspecified Cox models, Analysis of generalized Bregman surrogate algorithms for nonsmooth nonconvex statistical learning, Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean, Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation, High-dimensional generalized linear models incorporating graphical structure among predictors, Quantile regression feature selection and estimation with grouped variables using Huber approximation, Unnamed Item, Unnamed Item, On the robustness of minimum norm interpolators and regularized empirical risk minimizers, Structured estimation for the nonparametric Cox model, Optimal estimation and rank detection for sparse spiked covariance matrices, A no-free-lunch theorem for multitask learning, Sparse high-dimensional varying coefficient model: nonasymptotic minimax study, A group VISA algorithm for variable selection, ISLET: Fast and Optimal Low-Rank Tensor Regression via Importance Sketching

Uses Software

• hgam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• 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.
• Some theoretical results on the grouped variables Lasso
• Convex analysis and nonlinear optimization. Theory and examples.
• The sparsity and bias of the LASSO selection in high-dimensional linear regression
• The benefit of group sparsity
• Variable selection in nonparametric additive models
• Moment inequalities for sums of dependent random variables under projective conditions
• High-dimensional additive modeling
• The composite absolute penalties family for grouped and hierarchical variable selection
• Oracle inequalities for inverse problems
• Weak convergence and empirical processes. With applications to statistics
• On the asymptotic properties of the group lasso estimator for linear models
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional generalized linear models and the lasso
• Sparsity oracle inequalities for the Lasso
• Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators
• Support union recovery in high-dimensional multivariate regression
• Aggregation for Gaussian regression
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Nemirovski's Inequalities Revisited
• Stable recovery of sparse overcomplete representations in the presence of noise
• The Group Lasso for Logistic Regression
• Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
• Model Selection and Estimation in Regression with Grouped Variables
• An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias
• Introduction to nonparametric estimation