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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.