1 code implementation • 6 Mar 2023 • Pierre Bréchet, Katerina Papagiannouli, Jing An, Guido Montúfar
We consider a deep matrix factorization model of covariance matrices trained with the Bures-Wasserstein distance.
no code implementations • 4 Dec 2019 • Pierre Bréchet, Tao Wu, Thomas Möllenhoff, Daniel Cremers
We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT).