PAC-Bayesian Domain Adaptation Bounds for Multi-view learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

PAC-Bayesian Domain Adaptation Bounds for Multi-view learning

Résumé

This paper presents a series of new results for domain adaptation in the multi-view learning setting. The incorporation of multiple views in the domain adaptation was paid little attention in the previous studies (Germain et al., 2013; 2015a). In this way, we propose an analysis of generalization bounds with Pac-Bayesian theory to consolidate the two paradigms, which are currently treated separately.
Fichier principal
Vignette du fichier
PAC_BAYES_ICML.pdf (255.93 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04382619 , version 1 (09-01-2024)

Identifiants

  • HAL Id : hal-04382619 , version 1

Citer

Mehdi Hennequin, Khalid Benabdeslem, Haytham Elghazel. PAC-Bayesian Domain Adaptation Bounds for Multi-view learning. PAC-Bayes Meets Interactive Learning, Jul 2023, Hawaii-Honolulu, United States. ⟨hal-04382619⟩
26 Consultations
22 Téléchargements

Partager

Gmail Facebook X LinkedIn More