Issue |
ESAIM: PS
Volume 26, 2022
|
|
---|---|---|
Page(s) | 171 - 207 | |
DOI | https://doi.org/10.1051/ps/2022003 | |
Published online | 01 March 2022 |
Rate of convergence for geometric inference based on the empirical Christoffel function
1
Institut de Mathématiques de Toulouse, UMR5219. Université de Toulouse, CNRS. UT3,
31062
Toulouse, France.
2
Institut de Recherche en Informatique de Toulouse. Universite de Toulouse, CNRS. UT3,
31062
Toulouse, France.
* Corresponding author: francois.bachoc@math.univ-toulouse.fr
Received:
8
March
2021
Accepted:
8
February
2022
We consider the problem of estimating the support of a measure from a finite, independent, sample. The estimators which are considered are constructed based on the empirical Christoffel function. Such estimators have been proposed for the problem of set estimation with heuristic justifications. We carry out a detailed finite sample analysis, that allows us to select the threshold and degree parameters as a function of the sample size. We provide a convergence rate analysis of the resulting support estimation procedure. Our analysis establishes that we may obtain finite sample bounds which are comparable to existing rates for different set estimation procedures. Our results rely on concentration inequalities for the empirical Christoffel function and on estimates of the supremum of the Christoffel-Darboux kernel on sets with smooth boundaries, that can be considered of independent interest.
Mathematics Subject Classification: 62G05 / 42C05
Key words: Support estimation / christoffel function / concentration / finite sample / convergence rate
© The authors. Published by EDP Sciences, SMAI 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.