Is model selection possible for the $\ell_p$-loss? PCO estimation for regression models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lacour, Claire, Massart, Pascal, Rivoirard, Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908320597540864
author Lacour, Claire
Massart, Pascal
Rivoirard, Vincent
author_facet Lacour, Claire
Massart, Pascal
Rivoirard, Vincent
contents This paper addresses the problem of model selection in the sequence model $Y=θ+\varepsilonξ$, when $ξ$ is sub-Gaussian, for non-euclidian loss-functions. In this model, the Penalized Comparison to Overfitting procedure is studied for the weighted $\ell_p$-loss, $p\geq 1.$ Several oracle inequalities are derived from concentration inequalities for sub-Weibull variables. Using judicious collections of models and penalty terms, minimax rates of convergence are stated for Besov bodies $\mathcal{B}_{r,\infty}^s$. These results are applied to the functional model of nonparametric regression.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11217
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is model selection possible for the $\ell_p$-loss? PCO estimation for regression models
Lacour, Claire
Massart, Pascal
Rivoirard, Vincent
Statistics Theory
62G05, 62C20 (Primary) 62G08, 60E15 (Secondary)
This paper addresses the problem of model selection in the sequence model $Y=θ+\varepsilonξ$, when $ξ$ is sub-Gaussian, for non-euclidian loss-functions. In this model, the Penalized Comparison to Overfitting procedure is studied for the weighted $\ell_p$-loss, $p\geq 1.$ Several oracle inequalities are derived from concentration inequalities for sub-Weibull variables. Using judicious collections of models and penalty terms, minimax rates of convergence are stated for Besov bodies $\mathcal{B}_{r,\infty}^s$. These results are applied to the functional model of nonparametric regression.
title Is model selection possible for the $\ell_p$-loss? PCO estimation for regression models
topic Statistics Theory
62G05, 62C20 (Primary) 62G08, 60E15 (Secondary)
url https://arxiv.org/abs/2504.11217