Estimator selection in the Gaussian setting
From MaRDI portal
Abstract: We consider the problem of estimating the mean of a Gaussian vector with independent components of common unknown variance . Our estimation procedure is based on estimator selection. More precisely, we start with an arbitrary and possibly infinite collection of estimators of based on and, with the same data , aim at selecting an estimator among with the smallest Euclidean risk. No assumptions on the estimators are made and their dependencies with respect to may be unknown. We establish a non-asymptotic risk bound for the selected estimator. As particular cases, our approach allows to handle the problems of aggregation and model selection as well as those of choosing a window and a kernel for estimating a regression function, or tuning the parameter involved in a penalized criterion. We also derive oracle-type inequalities when consists of linear estimators. For illustration, we carry out two simulation studies. One aims at comparing our procedure to cross-validation for choosing a tuning parameter. The other shows how to implement our approach to solve the problem of variable selection in practice.
Recommendations
Cites work
- A survey of cross-validation procedures for model selection
- A universal procedure for aggregating estimators
- Adaptive Lasso for sparse high-dimensional regression models
- Adaptive Regression by Mixing
- Aggregation for Gaussian regression
- Asymptotically minimax adaptive estimation. II: Schemes without optimal adaption. Adaptive estimates
- Atomic Decomposition by Basis Pursuit
- Combining different procedures for adaptive regression
- Estimator selection in the Gaussian setting
- Estimator selection with respect to Hellinger-type risks
- Functional aggregation for nonparametric regression.
- Gaussian model selection
- Gaussian model selection with an unknown variance
- High-dimensional regression with unknown variance
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 4174160 (Why is no real title available?)
- scientific article; zbMATH DE number 28602 (Why is no real title available?)
- scientific article; zbMATH DE number 177229 (Why is no real title available?)
- scientific article; zbMATH DE number 1321826 (Why is no real title available?)
- scientific article; zbMATH DE number 1344902 (Why is no real title available?)
- scientific article; zbMATH DE number 1175931 (Why is no real title available?)
- scientific article; zbMATH DE number 1522808 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 4197203 (Why is no real title available?)
- scientific article; zbMATH DE number 3221828 (Why is no real title available?)
- scientific article; zbMATH DE number 3222478 (Why is no real title available?)
- Information Theory and Mixing Least-Squares Regressions
- Learning Bounds for Kernel Regression Using Effective Data Dimensionality
- Learning Theory and Kernel Machines
- Least angle regression. (With discussion)
- Linear and convex aggregation of density estimators
- Mixing least-squares estimators when the variance is unknown
- Mixing strategies for density estimation.
- Model selection by resampling penalization
- Model selection for regression on a fixed design
- Model selection in nonparametric regression
- Model selection via testing: an alternative to (penalized) maximum likelihood estimators.
- On the ``degrees of freedom of the lasso
- Random approximants and neural networks
- Random forests
- Regularization and Variable Selection Via the Elastic Net
- Ridge Regression: Applications to Nonorthogonal Problems
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Structural adaptation via \(\mathbb L_p\)-norm oracle inequalities
- The Adaptive Lasso and Its Oracle Properties
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
Cited in
(25)- Gaussian model selection with an unknown variance
- Estimator selection in the Gaussian setting
- A new approach to estimator selection
- Optimal bounds for aggregation of affine estimators
- Sharp oracle inequalities for aggregation of affine estimators
- Simultaneous estimation of the mean and the variance in heteroscedastic Gaussian regression
- Low rank multivariate regression
- Learning from MOM's principles: Le Cam's approach
- A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning
- Targeted cross-validation
- A global homogeneity test for high-dimensional linear regression
- Adaptive estimation over anisotropic functional classes via oracle approach
- Estimator selection
- General selection rule from a family of linear estimators
- LINselect
- Pre-Test type estimators for selection of simple normal models
- Post-selection point and interval estimation of signal sizes in Gaussian samples
- An alternative point of view on Lepski's method
- Variance Estimation in a Model With Gaussian Submodels
- High-dimensional regression with unknown variance
- Estimator selection with respect to Hellinger-type risks
- Adaptive nonparametric estimation in the functional linear model with functional output
- Some recent developments on functional data analysis
- Minimum discrepancy principle strategy for choosing k in k-NN regression
- Pointwise density estimation on metric spaces and applications in seismology
This page was built for publication: Estimator selection in the Gaussian setting
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q141397)
