DeepAI AI Chat
Log In Sign Up

Generative Modeling using the Sliced Wasserstein Distance

by   Ishan Deshpande, et al.

Generative Adversarial Nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often not stable. While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddle-point formulation. By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. Further, unlike the traditional GAN loss, the loss formulated in our method is a good measure of the actual distance between the distributions and, for the first time for GAN training, we are able to show estimates for the same.


page 1

page 6

page 7

page 12


From GAN to WGAN

This paper explains the math behind a generative adversarial network (GA...

Dualing GANs

Generative adversarial nets (GANs) are a promising technique for modelin...

A Convex Duality Framework for GANs

Generative adversarial network (GAN) is a minimax game between a generat...

Sliced Wasserstein Generative Models

In generative modeling, the Wasserstein distance (WD) has emerged as a u...

Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow

In this paper, we investigate the training process of generative network...

Max-Sliced Wasserstein Distance and its use for GANs

Generative adversarial nets (GANs) and variational auto-encoders have si...

Solving Approximate Wasserstein GANs to Stationarity

Generative Adversarial Networks (GANs) are one of the most practical str...

Code Repositories


IAN for neural photo editing

view repo