Wasserstein-Wasserstein Auto-Encoders

To address the challenges in learning deep generative models (e.g.,the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE). We formulate WWAE as minimizati...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-02
Main Authors: Zhang, Shunkang, Gao, Yuan, Jiao, Yuling, Liu, Jin, Wang, Yang, Yang, Can
Format: Article
Language:English
Subjects:
Coders
Mathematical analysis
Mathematical models
Optimization
Stability
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address the challenges in learning deep generative models (e.g.,the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE). We formulate WWAE as minimization of the penalized optimal transport between the target distribution and the generated distribution. By noticing that both the prior \(P_Z\) and the aggregated posterior \(Q_Z\) of the latent code Z can be well captured by Gaussians, the proposed WWAE utilizes the closed-form of the squared Wasserstein-2 distance for two Gaussians in the optimization process. As a result, WWAE does not suffer from the sampling burden and it is computationally efficient by leveraging the reparameterization trick. Numerical results evaluated on multiple benchmark datasets including MNIST, fashion- MNIST and CelebA show that WWAE learns better latent structures than VAEs and generates samples of better visual quality and higher FID scores than VAEs and GANs.
ISSN:2331-8422