Saved in:
Bibliographic Details
Main Authors: Leger, Victor, Couillet, Romain
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.13646
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910338955345920
author Leger, Victor
Couillet, Romain
author_facet Leger, Victor
Couillet, Romain
contents 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 enough to provide good performance guarantees, is also straightforward enough to provide strong insights into its behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13646
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Large Dimensional Analysis of Multi-task Semi-Supervised Learning
Leger, Victor
Couillet, Romain
Machine Learning
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 enough to provide good performance guarantees, is also straightforward enough to provide strong insights into its behavior.
title A Large Dimensional Analysis of Multi-task Semi-Supervised Learning
topic Machine Learning
url https://arxiv.org/abs/2402.13646