Asymptotic Bayes risk of semi-supervised learning with uncertain labeling

arXiv:2403.17767v1 Announce Type: cross
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.

abstract aim article arxiv bayes behavior classification compute cs.lg data labeling labels risk semi-supervised semi-supervised learning stat.ml supervised learning type uncertain