Minimax optimal rates of estimation in high dimensional additive models

DOI10.1214/15-AOS1422zbMath1360.62200arXiv1503.02817MaRDI QIDQ510684

Ding-Xuan Zhou, Ming Yuan

Publication date: 13 February 2017

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

Full work available at URL: https://arxiv.org/abs/1503.02817

zbMATH Keywords

Sobolev spaceconvergence ratereproducing kernel Hilbert spaceminimax optimalitymethod of regularization

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07)

Related Items (13)

An Online Projection Estimator for Nonparametric Regression in Reproducing Kernel Hilbert Spaces ⋮ Grouped variable selection with discrete optimization: computational and statistical perspectives ⋮ Kernel Ordinary Differential Equations ⋮ Nonparametric distributed learning under general designs ⋮ Minimax optimal estimation in partially linear additive models under high dimension ⋮ Regularizing Double Machine Learning in Partially Linear Endogenous Models ⋮ Kernel Knockoffs Selection for Nonparametric Additive Models ⋮ Oracle posterior contraction rates under hierarchical priors ⋮ Information based complexity for high dimensional sparse functions ⋮ Sparse additive machine with ramp loss ⋮ Doubly penalized estimation in additive regression with high-dimensional data ⋮ Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm ⋮ A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids

This page was built for publication: Minimax optimal rates of estimation in high dimensional additive models