A nearest neighbor characterization of Lebesgue points in metric measure spaces
Mathematical Statistics and Learning · 2021
DOI: 10.4171/msl/19 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Statistics and Learning, 2021. Verfasst von Tommaso R. Cesari und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
The property of almost every point being a Lebesgue point has proven to be crucial for the consistency of several classification algorithms based on nearest neighbors.We characterize Lebesgue points in terms of a 1-nearest neighbor regression algorithm for pointwise estimation, fleshing out the role played by tie-breaking rules in the corresponding convergence problem. We then give an application of our results, proving the convergence of the risk of a large class of 1-nearest neighbor classification algorithms in general metric spaces where almost every point is a Lebesgue point.
Zitieren
APA
Cesari, T. R., & Colomboni, R. (2021). A nearest neighbor characterization of Lebesgue points in metric measure spaces. Mathematical Statistics and Learning. https://doi.org/10.4171/msl/19
Vancouver
Cesari TR, Colomboni R. A nearest neighbor characterization of Lebesgue points in metric measure spaces. Mathematical Statistics and Learning. 2021. doi:10.4171/msl/19
BibTeX
@article{Cesari2021,
author = {Cesari, Tommaso R. and Colomboni, Roberto},
title = {A nearest neighbor characterization of Lebesgue points in metric measure spaces},
journal = {Mathematical Statistics and Learning},
year = {2021},
doi = {10.4171/msl/19}
}
EUVIMED