Exponential screening and optimal rates of sparse estimation
From MaRDI portal
Abstract: In high-dimensional linear regression, the goal pursued here is to estimate an unknown regression function using linear combinations of a suitable set of covariates. One of the key assumptions for the success of any statistical procedure in this setup is to assume that the linear combination is sparse in some sense, for example, that it involves only few covariates. We consider a general, non necessarily linear, regression with Gaussian noise and study a related question that is to find a linear combination of approximating functions, which is at the same time sparse and has small mean squared error (MSE). We introduce a new estimation procedure, called Exponential Screening that shows remarkable adaptation properties. It adapts to the linear combination that optimally balances MSE and sparsity, whether the latter is measured in terms of the number of non-zero entries in the combination ( norm) or in terms of the global weight of the combination ( norm). The power of this adaptation result is illustrated by showing that Exponential Screening solves optimally and simultaneously all the problems of aggregation in Gaussian regression that have been discussed in the literature. Moreover, we show that the performance of the Exponential Screening estimator cannot be improved in a minimax sense, even if the optimal sparsity is known in advance. The theoretical and numerical superiority of Exponential Screening compared to state-of-the-art sparse procedures is also discussed.
Recommendations
- Sparse estimation by exponential weighting
- PAC-Bayesian bounds for sparse regression estimation with exponential weights
- Estimation and variable selection with exponential weights
- Aggregation and minimax optimality in high-dimensional estimation
- Nearly optimal minimax estimator for high-dimensional sparse linear regression
Cites work
- scientific article; zbMATH DE number 3626409 (Why is no real title available?)
- scientific article; zbMATH DE number 409717 (Why is no real title available?)
- scientific article; zbMATH DE number 1522808 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- A simple proof of the restricted isometry property for random matrices
- Adapting to unknown sparsity by controlling the false discovery rate
- Adaptive estimation of the intensity of inhomogeneous Poisson processes via concentration inequalities
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Aggregation for Gaussian regression
- Combining Minimax Shrinkage Estimators
- Exponential screening and optimal rates of sparse estimation
- Generalized mirror averaging and D-convex aggregation
- High-dimensional generalized linear models and the lasso
- Ideal spatial adaptation by wavelet shrinkage
- Information Theory and Mixing Least-Squares Regressions
- Introduction to nonparametric estimation
- Learning Theory and Kernel Machines
- Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
- Minimax multiple shrinkage estimation
- Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
- Mirror averaging with sparsity priors
- Mixing least-squares estimators when the variance is unknown
- Nearly unbiased variable selection under minimax concave penalty
- On the conditions used to prove oracle results for the Lasso
- PAC-Bayesian bounds for sparse regression estimation with exponential weights
- Simultaneous analysis of Lasso and Dantzig selector
- Some sharp performance bounds for least squares regression with L₁ regularization
- Sparse regression learning by aggregation and Langevin Monte-Carlo
- Sparsity in penalized empirical risk minimization
- Sparsity oracle inequalities for the Lasso
- The Dantzig selector and sparsity oracle inequalities
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
- The elements of statistical learning. Data mining, inference, and prediction
- The restricted isometry property and its implications for compressed sensing
- The risk inflation criterion for multiple regression
- The sparsity and bias of the LASSO selection in high-dimensional linear regression
- Universal approximation bounds for superpositions of a sigmoidal function
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(69)- On cross-validated Lasso in high dimensions
- High-dimensional regression with unknown variance
- Aggregation of affine estimators
- Robust Bayes estimation using the density power divergence
- Sharp oracle inequalities for aggregation of affine estimators
- Covariate assisted screening and estimation
- Restricted strong convexity implies weak submodularity
- The smooth-Lasso and other \(\ell _{1}+\ell _{2}\)-penalized methods
- Targeting underrepresented populations in precision medicine: a federated transfer learning approach
- An \(\ell_1\)-oracle inequality for the Lasso in multivariate finite mixture of multivariate Gaussian regression models
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- Combining a relaxed EM algorithm with Occam's razor for Bayesian variable selection in high-dimensional regression
- Exponential screening and optimal rates of sparse estimation
- Statistical inference for data-adaptive doubly robust estimators with survival outcomes
- Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood
- On the prediction loss of the Lasso in the partially labeled setting
- Structured matrix estimation and completion
- Optimal learning with \textit{Q}-aggregation
- Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space
- Adaptive density estimation on bounded domains
- Structured, sparse aggregation
- Oracle inequalities for high-dimensional prediction
- Slope meets Lasso: improved oracle bounds and optimality
- Bayesian linear regression with sparse priors
- Exponential weights in multivariate regression and a low-rankness favoring prior
- Model selection in regression under structural constraints
- On Robustness of Principal Component Regression
- Estimation and variable selection with exponential weights
- Sharp oracle inequalities for low-complexity priors
- Prediction and estimation consistency of sparse multi-class penalized optimal scoring
- Entropic optimal transport is maximum-likelihood deconvolution
- Solution of linear ill-posed problems by model selection and aggregation
- Regularization and the small-ball method. II: Complexity dependent error rates
- Aggregated hold out for sparse linear regression with a robust loss function
- Optimal bounds for aggregation of affine estimators
- Mirror averaging with sparsity priors
- Sparse PCA: optimal rates and adaptive estimation
- Adaptive estimation over anisotropic functional classes via oracle approach
- Model-averaged \(\ell_1\) regularization using Markov chain Monte Carlo model composition
- Minimax risks for sparse regressions: ultra-high dimensional phenomenons
- Prediction error bounds for linear regression with the TREX
- Block-based refitting in \(\ell_{12}\) sparse regularization
- A new perspective on least squares under convex constraint
- PAC-Bayesian bounds for sparse regression estimation with exponential weights
- Statistical inference in compound functional models
- Sparse covariance matrix estimation in high-dimensional deconvolution
- Estimation of matrices with row sparsity
- Oracle inequalities for local and global empirical risk minimizers
- Upper bounds and aggregation in bipartite ranking
- A general framework for Bayes structured linear models
- Inference without compatibility: using exponential weighting for inference on a parameter of a linear model
- Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions
- Theory of adaptive estimation
- The Lasso as an \(\ell _{1}\)-ball model selection procedure
- On the exponentially weighted aggregate with the Laplace prior
- Empirical risk minimization is optimal for the convex aggregation problem
- MAP model selection in Gaussian regression
- Kullback-Leibler aggregation and misspecified generalized linear models
- Comment on ``Hypothesis testing by convex optimization
- Deviation optimal learning using greedy \(Q\)-aggregation
- Oracle inequalities for high dimensional vector autoregressions
- Estimation of high-dimensional low-rank matrices
- Isotonic regression meets Lasso
- CLEAR: covariant least-square refitting with applications to image restoration
- Oracle inequalities and optimal inference under group sparsity
- Sparse estimation by exponential weighting
- Covariate-adaptive randomization with variable selection in clinical trials
- Estimation and Inference for High-Dimensional Generalized Linear Models with Knowledge Transfer
- Transfer Learning in Large-Scale Gaussian Graphical Models with False Discovery Rate Control
This page was built for publication: Exponential screening and optimal rates of sparse estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q548534)
