2000 character limit reached
On the Latent Space of Wasserstein Auto-Encoders (1802.03761v1)
Published 11 Feb 2018 in stat.ML and cs.LG
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. We highlight the potential of WAEs for representation learning with promising results on a benchmark disentanglement task.