Classification and Regression Error Bounds for Inhomogenous Data With Applications to Wireless Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Ganesan, Ghurumuruhan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911825700847616
author Ganesan, Ghurumuruhan
author_facet Ganesan, Ghurumuruhan
contents In this paper, we study classification and regression error bounds for inhomogenous data that are independent but not necessarily identically distributed. First, we consider classification of data in the presence of non-stationary noise and establish ergodic type sufficient conditions that guarantee the achievability of the Bayes error bound, using universal rules. We then perform a similar analysis for $k$-nearest neighbour regression and obtain optimal error bounds for the same. Finally, we illustrate applications of our results in the context of wireless networks.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02262
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classification and Regression Error Bounds for Inhomogenous Data With Applications to Wireless Networks
Ganesan, Ghurumuruhan
Information Theory
Probability
In this paper, we study classification and regression error bounds for inhomogenous data that are independent but not necessarily identically distributed. First, we consider classification of data in the presence of non-stationary noise and establish ergodic type sufficient conditions that guarantee the achievability of the Bayes error bound, using universal rules. We then perform a similar analysis for $k$-nearest neighbour regression and obtain optimal error bounds for the same. Finally, we illustrate applications of our results in the context of wireless networks.
title Classification and Regression Error Bounds for Inhomogenous Data With Applications to Wireless Networks
topic Information Theory
Probability
url https://arxiv.org/abs/2404.02262