PCA-based Multi Task Learning: a Random Matrix Approach - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

PCA-based Multi Task Learning: a Random Matrix Approach

Malik Tiomoko
  • Fonction : Auteur
  • PersonId : 1091598

Résumé

The article proposes and theoretically analyses a computationally efficient multi-task learning (MTL) extension of popular principal component analysis (PCA)-based supervised learning schemes [7, 5]. The analysis reveals that (i) by default learning may dramatically fail by suffering from negative transfer, but that (ii) simple countermeasures 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.
Fichier principal
Vignette du fichier
tiomoko23a.pdf (523.59 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03420009 , version 1 (08-11-2021)
hal-03420009 , version 2 (22-01-2024)

Identifiants

  • HAL Id : hal-03420009 , version 2

Citer

Malik Tiomoko, Romain Couillet, Frédéric Pascal. PCA-based Multi Task Learning: a Random Matrix Approach. Proceedings of the 40th International Conference on Machine Learning, PMLR 202, Jul 2023, Honololu, Hawaii, United States. pp.34280-34300. ⟨hal-03420009v2⟩
64 Consultations
40 Téléchargements

Partager

Gmail Facebook X LinkedIn More