GAN and VAE from an Optimal Transport Point of View
Aude Genevay
and
Gabriel Peyré
and
Marco Cuturi
arXiv e-Print archive - 2017 via Local arXiv
Keywords:
stat.ML
First published: 2017/06/06 (6 years ago) Abstract: This short article revisits some of the ideas introduced in arXiv:1701.07875
and arXiv:1705.07642 in a simple setup. This sheds some lights on the
connexions between Variational Autoencoders (VAE), Generative Adversarial
Networks (GAN) and Minimum Kantorovitch Estimators (MKE).