mlsanityData to 7 Oct 2026

Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture

arXiv 2303.02048 ↗First posted 3 Mar 2023stat.ML cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The article considers semi-supervised multitask learning on a Gaussian mixture model (GMM). Using methods from statistical physics, we compute the asymptotic Bayes risk of each task in the regime of large datasets in high dimension, from which we analyze the role of task similarity in learning and evaluate the performance gain when tasks are learned together rather than separately. In the supervised case, we derive a simple algorithm that attains the Bayes optimal performance.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 10 of its 26 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

10 of 26 references.

References · 10

  1. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  2. 2017Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Modelscited by 115
  3. 2020The role of regularization in classification of high-dimensional noisy Gaussian mixturecited by 63
  4. 2021Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensionscited by 52
  5. 2020Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimizationcited by 51
  6. 2020Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic Viewcited by 32
  7. 2019Asymptotic Bayes risk for Gaussian mixture in a semi-supervised settingcited by 15
  8. 2016Phase transitions and optimal algorithms in high-dimensional Gaussian mixture clusteringcited by 13
  9. 2020Consistent Semi-Supervised Graph Regularization for High Dimensional Datacited by 10
  10. 2021PCA-based Multi Task Learning: a Random Matrix Approachcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 4.

4 papers.

  1. 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecastingcited by 7
  2. 2024A Large Dimensional Analysis of Multi-task Semi-Supervised Learningcited by 1
  3. 2024Asymptotic Bayes risk of semi-supervised learning with uncertain labelingcited by 0
  4. 2024Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networkscited by 0