Search Results for author:
Found 3 papers, 0 papers with code
Inferential Wasserstein Generative Adversarial Networks
The Wasserstein GAN (WGAN) leverages the Wasserstein distance to avoid the caveats in the minmax two-player training of GANs but has other defects such as mode collapse and lack of metric to detect the convergence.
iWGAN: an Autoencoder WGAN for Inference
We further provide a rigorous probabilistic interpretation of our model under the framework of maximum likelihood estimation.
A Uniform Generalization Error Bound for Generative Adversarial Networks
To better understand the unsupervised model, GANs, we establish the generalization bound, which uniformly holds with respect to the choice of generators.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
