Asymptotic Bayes risk of semi-supervised learning with uncertain labeling
This work addresses classification with uncertain labels, a problem for machine learning practitioners, but it appears incremental as it focuses on theoretical analysis within a specific model.
The paper tackled semi-supervised classification with uncertain labels in a Gaussian mixture model, computing the Bayes risk and comparing it to the best known algorithm to provide new insights into the algorithm's performance.
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.