Fiche du document
2019
- handle: 10670/1.ms70ov
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/urn/urn:nbn:ch:serval-BIB_606AA27EDB599
info:eu-repo/semantics/openAccess , Copying allowed only for non-profit organizations , https://serval.unil.ch/disclaimer
Citer ce document
Natasa Tagasovska et al., « Copulas as High Dimensional Generative Models: Vine Copula Autoencoders », Serveur académique Lausannois, ID : 10670/1.ms70ov
Métriques
Partage / Export
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.