Penalized least squares estimation in the additive model with different smoothness for the components

DOI10.1016/J.JSPI.2015.02.003zbMath1328.62256arXiv1405.6584OpenAlexW2049932513MaRDI QIDQ2348102

Alan Muro, Sara van de Geer

Publication date: 10 June 2015

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Abstract: We consider an additive regression model consisting of two components $f^0$ and $g^0$, where the first component $f^0$ is in some sense "smoother" than the second $g^0$. Smoothness is here described in terms of a semi-norm on the class of regression functions. We use a penalized least squares estimator $(hat f, hat g)$ of $(f^0, g^0)$ and show that the rate of convergence for $hat f $ is faster than the rate of convergence for $hat g$. In fact, both rates are generally as fast as in the case where one of the two components is known. The theory is illustrated by a simulation study. Our proofs rely on recent results from empirical process theory.

Full work available at URL: https://arxiv.org/abs/1405.6584

zbMATH Keywords

smoothnessadditive modelpenalized least squaresoracle rate

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric estimation (62G05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The existence and asymptotic properties of a backfitting projection algorithm under weak conditions
• Nonparametric regression with the scale depending on auxiliary variable
• Optimal estimation in additive regression models
• Subspaces and orthogonal decompositions generated by bounded orthogonal systems
• Additive regression and other nonparametric models
• Weak convergence and empirical processes. With applications to statistics
• On the conditions used to prove oracle results for the Lasso
• An adaptive compression algorithm in Besov spaces
• Statistical inference in compound functional models
• On the uniform convergence of empirical norms and inner products, with application to causal inference
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• The Partial Linear Model in High Dimensions
• A practical guide to splines.

Related Items (6)

Slope heuristics and V-Fold model selection in heteroscedastic regression using strongly localized bases ⋮ On concentration for (regularized) empirical risk minimization ⋮ On the uniform convergence of empirical norms and inner products, with application to causal inference ⋮ Minimax optimal estimation in partially linear additive models under high dimension ⋮ Gradient-based Regularization Parameter Selection for Problems With Nonsmooth Penalty Functions ⋮ Unnamed Item

This page was built for publication: Penalized least squares estimation in the additive model with different smoothness for the components