Communication Dans Un Congrès Année : 2014

An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context

Résumé

This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germain et al. in two ways. We first give another generalization bound tighter and easier to interpret. Moreover, we provide a new analysis of the constant term appearing in the bound that can be of high interest for developing new algorithmic solutions.

Fichier principal
Vignette du fichier
improvment_pbda.pdf (99.2 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-01093565 , version 1 (10-12-2014)
hal-01093565 , version 2 (13-01-2015)

Licence

Identifiants

Citer

Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant. An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context. NIPS 2014 Workshop on Transfer and Multi-task learning: Theory Meets Practice, Dec 2014, Montréal, Canada. ⟨hal-01093565v2⟩
173 Consultations
221 Téléchargements

Altmetric

Partager

  • More