Thumbnail

X-Ray Sobolev Variational Auto-Encoders

Turinici, Gabriel (2019), X-Ray Sobolev Variational Auto-Encoders. https://basepub.dauphine.fr/handle/123456789/20349

Voir/Ouvrir
Type
Document de travail / Working paper
Lien vers un document non conservé dans cette base
https://hal.archives-ouvertes.fr/hal-02387084
Date
2019
Éditeur
Cahier de recherche CEREMADE, Université Paris-Dauphine
Titre de la collection
Cahier de recherche CEREMADE, Université Paris-Dauphine
Ville d’édition
Paris
Pages
26
Métadonnées
Afficher la notice complète
Auteur(s)
Turinici, Gabriel cc
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Résumé (EN)
The quality of the generative models (Generative adversarial networks, Variational Auto-Encoders, ...) depends heavily on the choice of a good probability distance. However some popular metrics lack convenient properties such as (geodesic) convexity, fast evaluation and so on. To address these shortcomings, we introduce a class of distances that have built-in convexity. We investigate the relationship with some known paradigms (sliced distances, reproducing kernel Hilbert spaces, energy distances). The distances are shown to posses fast implementations and are included in an adapted Variational Auto-Encoder termed X-ray Sobolev Variational Auto-Encoder (XS-VAE) which produces good quality results on standard generative datasets.
Mots-clés
machine learning; variational auto-encoder; neural network; deep learning