Search Results for author:
Found 4 papers, 0 papers with code
{Learning disentangled representations with the Wasserstein Autoencoder
We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where we expect improved reconstructions due to the flexibility of the WAE paradigm.
Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
Probabilistic models with hierarchical-latent-variable structures provide state-of-the-art results amongst non-autoregressive, unsupervised density-based models.
Learning disentangled representations with the Wasserstein Autoencoder
We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where the flexibility of the WAE paradigm in the reconstruction term improves reconstructions.
Gaussian mixture models with Wasserstein distance
Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets.
