A Large Dimensional Analysis of Multi-task Semi-Supervised Learning

arXiv:2402.13646v1 Announce Type: cross
Abstract: This article conducts a large dimensional study of a simple yet quite versatile classification model, encompassing at once multi-task and semi-supervised learning, and taking into account uncertain labeling. Using tools from random matrix theory, we characterize the asymptotics of some key functionals, which allows us on the one hand to predict the performances of the algorithm, and on the other hand to reveal some counter-intuitive guidance on how to use it efficiently. The model, powerful …

abstract analysis article arxiv classification classification model cs.lg key labeling matrix random semi-supervised semi-supervised learning simple stat.ml study supervised learning theory tools type uncertain