Online Consistency of the Nearest Neighbor Rule

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dasgupta, Sanjoy, So, Geelon
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910678993862656
author Dasgupta, Sanjoy
So, Geelon
author_facet Dasgupta, Sanjoy
So, Geelon
contents In the realizable online setting, a learner is tasked with making predictions for a stream of instances, where the correct answer is revealed after each prediction. A learning rule is online consistent if its mistake rate eventually vanishes. The nearest neighbor rule (Fix and Hodges, 1951) is a fundamental prediction strategy, but it is only known to be consistent under strong statistical or geometric assumptions: the instances come i.i.d. or the label classes are well-separated. We prove online consistency for all measurable functions in doubling metric spaces under the mild assumption that the instances are generated by a process that is uniformly absolutely continuous with respect to a finite, upper doubling measure.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23644
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Consistency of the Nearest Neighbor Rule
Dasgupta, Sanjoy
So, Geelon
Machine Learning
In the realizable online setting, a learner is tasked with making predictions for a stream of instances, where the correct answer is revealed after each prediction. A learning rule is online consistent if its mistake rate eventually vanishes. The nearest neighbor rule (Fix and Hodges, 1951) is a fundamental prediction strategy, but it is only known to be consistent under strong statistical or geometric assumptions: the instances come i.i.d. or the label classes are well-separated. We prove online consistency for all measurable functions in doubling metric spaces under the mild assumption that the instances are generated by a process that is uniformly absolutely continuous with respect to a finite, upper doubling measure.
title Online Consistency of the Nearest Neighbor Rule
topic Machine Learning
url https://arxiv.org/abs/2410.23644