Titre :

Sliced-Wasserstein normalizing flows: beyond maximum likelihood training

Auteur(s) :

Coeurdoux, Florentin [Auteur]
Signal et Communications [IRIT-SC]
Dobigeon, Nicolas [Auteur]
Institut universitaire de France [IUF]
Signal et Communications [IRIT-SC]
Chainais, Pierre [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Titre de la manifestation scientifique :

30th European Symposium on Artificial Neural Networks (ESANN 2022)

Ville :

Bruges

Pays :

Belgique

Date de début de la manifestation scientifique :

2022-10-05

Titre de l’ouvrage :

à paraître

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Réseau de neurones [cs.NE]

Résumé en anglais : [en]

Despite their advantages, normalizing flows generally suffer from several shortcomings including their tendency to generate unrealistic data (e.g., images) and their failing to detect out-of-distribution data. One reason ...
Lire la suite >Despite their advantages, normalizing flows generally suffer from several shortcomings including their tendency to generate unrealistic data (e.g., images) and their failing to detect out-of-distribution data. One reason for these deficiencies lies in the training strategy which traditionally exploits a maximum likelihood principle only. This paper proposes a new training paradigm based on a hybrid objective function combining the maximum likelihood principle (MLE) and a sliced-Wasserstein distance. Results obtained on synthetic toy examples and real image data sets show better generative abilities in terms of both likelihood and visual aspects of the generated samples. Reciprocally, the proposed approach leads to a lower likelihood of out-of-distribution data, demonstrating a greater data fidelity of the resulting flows.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Artificial and Natural Intelligence Toulouse Institute

Commentaire :

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL