Copulas as High Dimensional Generative Models: Vine Copula Autoencoders
Détails
Etat: Public
Version: Final published version
Licence: Non spécifiée
ID Serval
serval:BIB_606AA27EDB59
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Institution
Titre
Copulas as High Dimensional Generative Models: Vine Copula Autoencoders
Titre de la conférence
Advances in Neural Information Processing Systems
Statut éditorial
Publié
Date de publication
2019
Pages
6525-6537
Langue
anglais
Résumé
We introduce the vine copula autoencoder (VCAE), a flexible generative model
for high-dimensional distributions built in a straightforward three-step procedure.
First, an autoencoder (AE) compresses the data into a lower dimensional representation. Second, the multivariate distribution of the encoded data is estimated with
vine copulas. Third, a generative model is obtained by combining the estimated
distribution with the decoder part of the AE. As such, the proposed approach
can transform any already trained AE into a flexible generative model at a low
computational cost. This is an advantage over existing generative models such as
adversarial networks and variational AEs which can be difficult to train and can
impose strong assumptions on the latent space. Experiments on MNIST, Street
View House Numbers and Large-Scale CelebFaces Attributes datasets show that
VCAEs can achieve competitive results to standard baselines.
for high-dimensional distributions built in a straightforward three-step procedure.
First, an autoencoder (AE) compresses the data into a lower dimensional representation. Second, the multivariate distribution of the encoded data is estimated with
vine copulas. Third, a generative model is obtained by combining the estimated
distribution with the decoder part of the AE. As such, the proposed approach
can transform any already trained AE into a flexible generative model at a low
computational cost. This is an advantage over existing generative models such as
adversarial networks and variational AEs which can be difficult to train and can
impose strong assumptions on the latent space. Experiments on MNIST, Street
View House Numbers and Large-Scale CelebFaces Attributes datasets show that
VCAEs can achieve competitive results to standard baselines.
Création de la notice
19/03/2020 16:07
Dernière modification de la notice
30/09/2020 7:09
Données d'usage
