Optimal bounds for aggregation of affine estimators
The author investigates the problem of aggregating a collection of affine estimators in a heteroscedastic regression model with Gaussian additive noise. The estimators are not independent of the data used for the aggregation. This leads to the question whether well-known minimax rates which hold for deterministic estimators remain valid or whether the variances of the estimators and their dependence increase the price to pay for aggregation because of statistical complexity. It is proven that for affine estimators, the minimax rate of aggregation is unchanged. The author defines a penalized procedure over the complex hull of the estimators and shows that it achieves sharp oracle inequalities in deviation for aggregation of affine estimators. The penalty term is inspired from the \(Q\)-aggregation procedure. Moreover, it is shown that the penalized aggregate is robust to non-Gaussian noise and to a certain variance misspecification.
- A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
- A bound on tail probabilities for quadratic forms in independent random variables whose distributions are not necessarily symmetric
- Adaptive estimation of a quadratic functional by model selection.
- Aggregation and minimax optimality in high-dimensional estimation
- Aggregation of affine estimators
- All Admissible Linear Estimates of the Mean Vector
- Asymptotically optimal difference-based estimation of variance in nonparametric regression
- Concentration inequalities. A nonasymptotic theory of independence
- Deviation optimal learning using greedy \(Q\)-aggregation
- Empirical risk minimization is optimal for the convex aggregation problem
- Estimating the Variance In Nonparametric Regression—What is a Reasonable Choice?
- Estimator selection in the Gaussian setting
- Exponential screening and optimal rates of sparse estimation
- Hanson-Wright inequality and sub-Gaussian concentration
- High-dimensional regression with unknown variance
- scientific article; zbMATH DE number 1522808 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- Information Theory and Mixing Least-Squares Regressions
- Introduction to nonparametric estimation
- Kullback-Leibler aggregation and misspecified generalized linear models
- Learning Theory and Kernel Machines
- Least squares after model selection in high-dimensional sparse models
- Linear and convex aggregation of density estimators
- Minimax risk over hyperrectangles, and implications
- Mixing least-squares estimators when the variance is unknown
- On Difference-Based Variance Estimation in Nonparametric Regression When the Covariate is High Dimensional
- Optimal exponential bounds for aggregation of density estimators
- Optimal learning with \textit{Q}-aggregation
- Pivotal estimation via square-root lasso in nonparametric regression
- Scaled sparse linear regression
- Sharp oracle inequalities for aggregation of affine estimators
- Some Comments on C P
- Sparse estimation by exponential weighting
- Tail and moment estimates for some types of chaos
- Solution of linear ill-posed problems by model selection and aggregation
- Limit theory in monotone function estimation
- Sharp oracle inequalities for aggregation of affine estimators
- A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning
- Second-order Stein: SURE for SURE and other applications in high-dimensional inference
- Aggregating estimates by convex optimization
- Exponential weights in multivariate regression and a low-rankness favoring prior
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- PAC-Bayesian aggregation of affine estimators
- Aggregation of affine estimators
- Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions
- Model averaging: a shrinkage perspective
- Extrapolated Cross-Validation for Randomized Ensembles
- Precise asymptotics of bagging regularized M-estimators
- Exponentially weighted averaging of varying-coefficient partially linear models
This page was built for publication: Optimal bounds for aggregation of affine estimators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1747732)
