Wasserstein Auto-Encoders: Latent Dimensionality and Random EncodersDownload PDF

Feb 12, 2018 (edited Jun 04, 2018)ICLR 2018 Workshop SubmissionReaders: Everyone
  • Keywords: wasserstein auto-encoders, WAE
  • TL;DR: We study the role of latent dimensionality in Wasserstein Auto-Encoders, and show that random encoders may often be preferable to deterministic encoders.
  • 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.
5 Replies