DeepAI AI Chat
Log In Sign Up

The Inductive Bias of Restricted f-GANs

by   Shuang Liu, et al.
University of California, San Diego

Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative adversarial learning -- that is, statistical inference as the result of a game between a generator and a discriminator -- with the view of understanding how it differs from classical statistical inference solutions such as maximum likelihood inference and the method of moments. Specifically, we provide a theoretical characterization of the distribution inferred by a simple form of generative adversarial learning called restricted f-GANs -- where the discriminator is a function in a given function class, the distribution induced by the generator is restricted to lie in a pre-specified distribution class and the objective is similar to a variational form of the f-divergence. A consequence of our result is that for linear KL-GANs -- that is, when the discriminator is a linear function over some feature space and f corresponds to the KL-divergence -- the distribution induced by the optimal generator is neither the maximum likelihood nor the method of moments solution, but an interesting combination of both.


page 1

page 2

page 3

page 4


A Convenient Infinite Dimensional Framework for Generative Adversarial Learning

In recent years, generative adversarial networks (GANs) have demonstrate...

Approximation and Convergence Properties of Generative Adversarial Learning

Generative adversarial networks (GAN) approximate a target data distribu...

Statistical inference for generative adversarial networks

This paper studies generative adversarial networks (GANs) from a statist...

KALE: When Energy-Based Learning Meets Adversarial Training

Legendre duality provides a variational lower-bound for the Kullback-Lei...

Approximability of Discriminators Implies Diversity in GANs

While Generative Adversarial Networks (GANs) have empirically produced i...

On the Discrimination-Generalization Tradeoff in GANs

Generative adversarial training can be generally understood as minimizin...

Bridging Maximum Likelihood and Adversarial Learning via α-Divergence

Maximum likelihood (ML) and adversarial learning are two popular approac...