mlsanityData to 7 Oct 2026

PCA-based Multi Task Learning: a Random Matrix Approach

arXiv 2111.00924 ↗First posted 1 Nov 2021stat.ML cs.LG math.STcited by 4

Not on the map. Why?

Abstract (arXiv)

The article proposes and theoretically analyses a computationally efficient multi-task learning (MTL) extension of popular principal component analysis (PCA)-based supervised learning schemes citebarshan2011supervised,bair2006prediction. The analysis reveals that (i) by default learning may dramatically fail by suffering from negative transfer, but that (ii) simple counter-measures on data labels avert negative transfer and necessarily result in improved performances. Supporting experiments on synthetic and real data benchmarks show that the proposed method achieves comparable performance with state-of-the-art MTL methods but at a significantly reduced computational cost.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 65 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

18 of 65 references.

References · 18

  1. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  2. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  3. 2017A Survey on Multi-Task Learningcited by 838
  4. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  5. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  6. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  7. 2018A Survey on Deep Transfer Learningcited by 417
  8. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  9. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 246
  10. 2020Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixturescited by 47
  11. 2013Efficient Learning of Domain-invariant Image Representationscited by 20
  12. 2017Semi-supervised Multitask Learning for Sequence Labelingcited by 20
6 more
  1. 2019Asymptotic Bayes risk for Gaussian mixture in a semi-supervised settingcited by 15
  2. 2019Unsupervised and Supervised Principal Component Analysis: Tutorialcited by 12
  3. 2020Large Dimensional Analysis and Improvement of Multi Task Learningcited by 9
  4. 2021Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clusteringcited by 7
  5. 2015Safe Screening for Multi-Task Feature Learning with Multiple Data Matricescited by 4
  6. 2021Supervised Principal Component Regression for Functional Responses with High Dimensional Predictorscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2024Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecastingcited by 7
  2. 2023Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumptioncited by 6
  3. 2023Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixturecited by 4
  4. 2025Incorporating priors in learning: a random matrix study under a teacher-student frameworkcited by 1