Approximation and Convergence Properties of Generative Adversarial Learning

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

Generative adversarial networks (GAN) approximate a target data distribution by jointly optimizing an objective function through a "two-player game" between a generator and a discriminator. Despite their empirical success, however, two very basic questions on how well they can approximate the target distribution remain unanswered. First, it is not known how restricting the discriminator family affects the approximation quality. Second, while a number of different objective functions have been proposed, we do not understand when convergence to the global minima of the objective function leads to convergence to the target distribution under various notions of distributional convergence. In this paper, we address these questions in a broad and unified setting by defining a notion of adversarial divergences that includes a number of recently proposed objective functions. We show that if the objective function is an adversarial divergence with some additional conditions, then using a restricted discriminator family has a moment-matching effect. Additionally, we show that for objective functions that are strict adversarial divergences, convergence in the objective function implies weak convergence, thus generalizing previous results.


page 1

page 2

page 3

page 4


The Inductive Bias of Restricted f-GANs

Generative adversarial networks are a novel method for statistical infer...

Some Theoretical Properties of GANs

Generative Adversarial Networks (GANs) are a class of generative algorit...

Contrastive Divergence Learning is a Time Reversal Adversarial Game

Contrastive divergence (CD) learning is a classical method for fitting u...

Multi-Agent Diverse Generative Adversarial Networks

This paper describes an intuitive generalization to the Generative Adver...

Annealed Generative Adversarial Networks

We introduce a novel framework for adversarial training where the target...

Convergence of GANs Training: A Game and Stochastic Control Methodology

Training of generative adversarial networks (GANs) is known for its diff...

Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models

Consider the problem of simultaneous estimation of location and variance...

Please sign up or login with your details

Forgot password? Click here to reset