## Frontmatter | | | | --- | --- | | Authors | [[Luca Ambrogioni]], [[Umut Güçlü]], [[Marcel van Gerven]] | | Date | 2019/07 | | Source | [[arXiv]] | | URL | https://doi.org/10.48550/arXiv.1907.04050 | | Citation | Ambrogioni, L., Güçlü, U., & van Gerven, M. (2019). [[k-GANs - Ensemble of generative models with semi-discrete optimal transport]]. _arXiv_. [[URL](https://doi.org/10.48550/arXiv.1907.04050)]. #Preprint | ## Abstract Generative adversarial networks (GANs) are the state of the art in generative modeling. Unfortunately, most GAN methods are susceptible to mode collapse, meaning that they tend to capture only a subset of the modes of the true distribution. A possible way of dealing with this problem is to use an ensemble of GANs, where (ideally) each network models a single mode. In this paper, we introduce a principled method for training an ensemble of GANs using semi-discrete optimal transport theory. In our approach, each generative network models the transportation map between a point mass (Dirac measure) and the restriction of the data distribution on a tile of a Voronoi tessellation that is defined by the location of the point masses. We iteratively train the generative networks and the point masses until convergence. The resulting k-GANs algorithm has strong theoretical connection with the k-medoids algorithm. In our experiments, we show that our ensemble method consistently outperforms baseline GANs. ## PDF ![[k-GANs - Ensemble of generative models with semi-discrete optimal transport.pdf]]