Asymptotic Bayes risk of semi-supervised learning with uncertain labeling
Machine Learning
2024-03-28 v2 Machine Learning
Abstract
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.
Keywords
Cite
@article{arxiv.2403.17767,
title = {Asymptotic Bayes risk of semi-supervised learning with uncertain labeling},
author = {Victor Leger and Romain Couillet},
journal= {arXiv preprint arXiv:2403.17767},
year = {2024}
}