DeepAI AI Chat
Log In Sign Up

Tessellated Wasserstein Auto-Encoders

by   Kuo Gai, et al.

Non-adversarial generative models such as variational auto-encoder (VAE), Wasserstein auto-encoders with maximum mean discrepancy (WAE-MMD), sliced-Wasserstein auto-encoder (SWAE) are relatively easy to train and have less mode collapse compared to Wasserstein auto-encoder with generative adversarial network (WAE-GAN). However, they are not very accurate in approximating the target distribution in the latent space because they don't have a discriminator to detect the minor difference between real and fake. To this end, we develop a novel non-adversarial framework called Tessellated Wasserstein Auto-encoders (TWAE) to tessellate the support of the target distribution into a given number of regions by the centroidal Voronoi tessellation (CVT) technique and design batches of data according to the tessellation instead of random shuffling for accurate computation of discrepancy. Theoretically, we demonstrate that the error of estimate to the discrepancy decreases when the numbers of samples n and regions m of the tessellation become larger with rates of O(1/√(n)) and O(1/√(m)), respectively. Given fixed n and m, a necessary condition for the upper bound of measurement error to be minimized is that the tessellation is the one determined by CVT. TWAE is very flexible to different non-adversarial metrics and can substantially enhance their generative performance in terms of Fréchet inception distance (FID) compared to VAE, WAE-MMD, SWAE. Moreover, numerical results indeed demonstrate that TWAE is competitive to the adversarial model WAE-GAN, demonstrating its powerful generative ability.


page 2

page 11

page 12

page 13


Wasserstein Auto-Encoders

We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for buil...

Closed-form Expressions for Maximum Mean Discrepancy with Applications to Wasserstein Auto-Encoders

The Maximum Mean Discrepancy (MMD) has found numerous applications in st...

Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation

Variational auto-encoders (VAEs) provide an attractive solution to image...

OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation

Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialo...

Causality Learning With Wasserstein Generative Adversarial Networks

Conventional methods for causal structure learning from data face signif...

A Simple Generative Network

Generative neural networks are able to mimic intricate probability distr...

X-Ray Sobolev Variational Auto-Encoders

The quality of the generative models (Generative adversarial networks, V...