Salvato in:
Dettagli Bibliografici
Autori principali: Leger, Victor, Couillet, Romain
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.17767
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929290823598080
author Leger, Victor
Couillet, Romain
author_facet Leger, Victor
Couillet, Romain
contents This article considers a semi-supervised classification setting on a Gaussian mixture model, where the data is not labeled strictly as usual, but instead with uncertain labels. Our main aim is to compute the Bayes risk for this model. We compare the behavior of the Bayes risk and the best known algorithm for this model. This comparison eventually gives new insights over the algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17767
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asymptotic Bayes risk of semi-supervised learning with uncertain labeling
Leger, Victor
Couillet, Romain
Machine Learning
This article considers a semi-supervised classification setting on a Gaussian mixture model, where the data is not labeled strictly as usual, but instead with uncertain labels. Our main aim is to compute the Bayes risk for this model. We compare the behavior of the Bayes risk and the best known algorithm for this model. This comparison eventually gives new insights over the algorithm.
title Asymptotic Bayes risk of semi-supervised learning with uncertain labeling
topic Machine Learning
url https://arxiv.org/abs/2403.17767