Salvato in:
Dettagli Bibliografici
Autore principale: Maillard, Guillaume
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.20239
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911021498630144
author Maillard, Guillaume
author_facet Maillard, Guillaume
contents We define a general method for finding a quasi-best approximant in sup-norm to a target density belonging to a given model, based on independent samples drawn from distributions which average to the target (which does not necessarily belong to the model). We also provide a general method for selecting among a countable family of such models. These estimators satisfy oracle inequalities in the general setting. The quality of the bounds depends on the volume of sets on which $|p-q|$ is close to its maximum, where $p,q$ belong to the model (or possibly to two different models, in the case of model selection). This leads to optimal results in a number of settings, including piecewise polynomials on a given partition and anisotropic smoothness classes. Particularly interesting is the case of the single index model with fixed smoothness $β$, where we recover the one-dimensional rate: this was an open problem.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20239
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A model-based approach to density estimation in sup-norm
Maillard, Guillaume
Statistics Theory
We define a general method for finding a quasi-best approximant in sup-norm to a target density belonging to a given model, based on independent samples drawn from distributions which average to the target (which does not necessarily belong to the model). We also provide a general method for selecting among a countable family of such models. These estimators satisfy oracle inequalities in the general setting. The quality of the bounds depends on the volume of sets on which $|p-q|$ is close to its maximum, where $p,q$ belong to the model (or possibly to two different models, in the case of model selection). This leads to optimal results in a number of settings, including piecewise polynomials on a given partition and anisotropic smoothness classes. Particularly interesting is the case of the single index model with fixed smoothness $β$, where we recover the one-dimensional rate: this was an open problem.
title A model-based approach to density estimation in sup-norm
topic Statistics Theory
url https://arxiv.org/abs/2506.20239