Cramer-Wold AutoEncoder

Jacek Tabor, Szymon Knop, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

Abstract:

Assessing distance betweeen the true and the sample distribution is a key component of many state of the art generative models, such as Wasserstein Autoencoder (WAE). Inspired by prior work on Sliced-Wasserstein Autoencoders (SWAE) and
kernel smoothing we construct a new generative model – Cramer-Wold AutoEncoder (CWAE). CWAE cost function, based on introduced Cramer-Wold distance between samples, has a simple closed-form in the case of normal prior. As a consequence, while simplifying the optimization procedure (no need of sampling necessary to evaluate the distance function in the training loop), CWAE performance matches quantitatively and qualitatively that of WAE-MMD (WAE using maximum mean discrepancy based distance function) and often improves upon SWAE.

TL;DR: Inspired by prior work on Sliced-Wasserstein Autoencoders (SWAE) and kernel smoothing we construct a new generative model – Cramer-Wold AutoEncoder (CWAE).

Keywords: autoencoder, generative models, deep neural networks

Code: [ gmum/cwae](https://github.com/gmum/cwae) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=rkgwuiA9F7)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1805.09235/code)