Asymptotic Bayes Risk for Gaussian Mixture in a Semi-Supervised Setting
Asymptotic Bayes Risk for Gaussian Mixture in a Semi-Supervised Setting
复制标题
半监督环境中高斯混合的渐近贝叶斯风险
DOI:
10.1109/camsap45676.2019.9022623
复制
发表时间:
2019
期刊:
影响因子:
--
通讯作者:
Léo Miolane
中科院分区:
文献类型:
--
作者:
M. Lelarge;Léo Miolane
Semi-supervised learning (SSL) uses unlabeled data for training and has been shown to greatly improve performances when compared to a supervised approach on the labeled data available. This claim depends both on the amount of labeled data available and on the algorithm used. In this paper, we compute analytically the gap between the best fully-supervised approach on labeled data and the best semi-supervised approach using both labeled and unlabeled data, in a simple high-dimensional Gaussian mixture model. We quantify the best possible increase in performance obtained thanks to the unlabeled data, i.e. we compute the accuracy increase due to the information contained in the unlabeled data.