k-GANs trains an ensemble of GANs by mapping point masses to Voronoi tiles of the data distribution using semi-discrete optimal transport and iteratively optimizing both generators and point masses, outperforming baseline GANs.
GAN and VAE from an Optimal Transport Point of View
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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).
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
k-GANs trains an ensemble of GANs by mapping point masses to Voronoi tiles of the data distribution using semi-discrete optimal transport and iteratively optimizing both generators and point masses, outperforming baseline GANs.