Asymptotic optimality of the fast randomized versions of GCV and \(C_ L\) in ridge regression and regularization

DOI10.1214/aos/1176348380zbMath0754.62030OpenAlexW2006240830MaRDI QIDQ1184217

Didier A. Girard

Publication date: 28 June 1992

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

Full work available at URL: https://doi.org/10.1214/aos/1176348380

zbMATH Keywords

regularizationsmoothing splineslinear modelridge regressionasymptotic optimalitygeneralized cross-validationMonte Carlo techniquesfast randomized versions of GCVMallow's \(C(sub L)\)

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Asymptotic properties of nonparametric inference (62G20)

Related Items

Smoothing spline ANOVA for exponential families, with application to the Wisconsin epidemiological study of diabetic retinopathy. (The 1994 Neyman Memorial Lecture) ⋮ Asymptotic optimality of a multivariate version of the generalized cross validation in adaptive smoothing splines ⋮ Scalable Algorithms for the Sparse Ridge Regression ⋮ Automatic Smoothing for Poisson Regression ⋮ Estimating the accuracy of (local) cross-validation via randomised GCV choices in kernel or smoothing spline regression ⋮ The General Expressions for the Moments of the Stochastic Shrinkage Parameters of the Liu Type Estimator ⋮ Asymptotic comparison of (partial) cross-validation, GCV and randomized GCV in nonparametric regression ⋮ Least trimmed squares ridge estimation in partially linear regression models