DeepAI AI Chat
Log In Sign Up

Sobolev GAN

by   Youssef Mroueh, et al.
Max Planck Society
Carnegie Mellon University

We propose a new Integral Probability Metric (IPM) between distributions: the Sobolev IPM. The Sobolev IPM compares the mean discrepancy of two distributions for functions (critic) restricted to a Sobolev ball defined with respect to a dominant measure μ. We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis. The Dominant measure μ plays a crucial role as it defines the support on which conditional CDFs are compared. Sobolev IPM can be seen as an extension of the one dimensional Von-Mises Cramér statistics to high dimensional distributions. We show how Sobolev IPM can be used to train Generative Adversarial Networks (GANs). We then exploit the intrinsic conditioning implied by Sobolev IPM in text generation. Finally we show that a variant of Sobolev GAN achieves competitive results in semi-supervised learning on CIFAR-10, thanks to the smoothness enforced on the critic by Sobolev GAN which relates to Laplacian regularization.


Semi-Supervised Learning with IPM-based GANs: an Empirical Study

We present an empirical investigation of a recent class of Generative Ad...

Fisher GAN

Generative Adversarial Networks (GANs) are powerful models for learning ...

Demystifying MMD GANs

We investigate the training and performance of generative adversarial ne...

Manifold regularization with GANs for semi-supervised learning

Generative Adversarial Networks are powerful generative models that are ...

Neural Stein critics with staged L^2-regularization

Learning to differentiate model distributions from observed data is a fu...

Reciprocal Adversarial Learning via Characteristic Functions

Generative adversarial nets (GANs) have become a preferred tool for acco...

A Characteristic Function Approach to Deep Implicit Generative Modeling

In this paper, we formulate the problem of learning an Implicit Generati...