Wasserstein Auto-Encoders: Latent Dimensionality and Random Encoders
Paul Rubenstein · Bernhard Schoelkopf · Ilya Tolstikhin
Abstract
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders.
Video
Chat is not available.
Successful Page Load