Data Interpolants – That's What Discriminators in Higher-order Gradient-regularized GANs Are

by   Siddarth Asokan, et al.

We consider the problem of optimizing the discriminator in generative adversarial networks (GANs) subject to higher-order gradient regularization. We show analytically, via the least-squares (LSGAN) and Wasserstein (WGAN) GAN variants, that the discriminator optimization problem is one of interpolation in n-dimensions. The optimal discriminator, derived using variational Calculus, turns out to be the solution to a partial differential equation involving the iterated Laplacian or the polyharmonic operator. The solution is implementable in closed-form via polyharmonic radial basis function (RBF) interpolation. In view of the polyharmonic connection, we refer to the corresponding GANs as Poly-LSGAN and Poly-WGAN. Through experimental validation on multivariate Gaussians, we show that implementing the optimal RBF discriminator in closed-form, with penalty orders m ≈⌈n/2⌉, results in superior performance, compared to training GAN with arbitrarily chosen discriminator architectures. We employ the Poly-WGAN discriminator to model the latent space distribution of the data with encoder-decoder-based GAN flavors such as Wasserstein autoencoders.


page 9

page 36

page 37

page 39

page 40

page 41


Adversarial network training using higher-order moments in a modified Wasserstein distance

Generative-adversarial networks (GANs) have been used to produce data cl...

Adaptive WGAN with loss change rate balancing

Optimizing the discriminator in Generative Adversarial Networks (GANs) t...

Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions

Generative Adversarial Networks (GANs) are commonly used for modeling co...

Lipschitz Generative Adversarial Nets

In this paper we study the convergence of generative adversarial network...

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs

We generalize the concept of maximum-margin classifiers (MMCs) to arbitr...

On Relativistic f-Divergences

This paper provides a more rigorous look at Relativistic Generative Adve...

Generative Adversarial Method Based on Neural Tangent Kernels

The recent development of Generative adversarial networks (GANs) has dri...

Please sign up or login with your details

Forgot password? Click here to reset