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

arXiv: https://arxiv.org/abs/2402.13646 · HTML: https://mlsanity.com/paper/2402.13646/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures](https://mlsanity.com/paper/2001.08370/) (2020)
- [A random matrix analysis and improvement of semi-supervised learning for large dimensional data](https://mlsanity.com/paper/1711.03404/) (2017)
- [Consistent Semi-Supervised Graph Regularization for High Dimensional Data](https://mlsanity.com/paper/2006.07575/) (2020)
- [Large Dimensional Analysis and Improvement of Multi Task Learning](https://mlsanity.com/paper/2009.01591/) (2020)
- [Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture](https://mlsanity.com/paper/2303.02048/) (2023)

## Built on by (most cited first, 1 of 1)

- [Asymptotic Bayes risk of semi-supervised learning with uncertain labeling](https://mlsanity.com/paper/2403.17767/) (2024)

## Abstract (arXiv)

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.