Convergence Problems with Generative Adversarial Networks (GANs)

06/29/2018
by   Samuel A. Barnett, et al.
4

Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine learning, in that they are best described as a two-player game between a discriminator and generator. This has yielded both unreliability in the training process, and a general lack of understanding as to how GANs converge, and if so, to what. The purpose of this dissertation is to provide an account of the theory of GANs suitable for the mathematician, highlighting both positive and negative results. This involves identifying the problems when training GANs, and how topological and game-theoretic perspectives of GANs have contributed to our understanding and improved our techniques in recent years.

READ FULL TEXT

page 7

page 12

page 34

research
03/30/2020

A game-theoretic approach for Generative Adversarial Networks

Generative adversarial networks (GANs) are a class of generative models,...
research
03/23/2018

Fictitious GAN: Training GANs with Historical Models

Generative adversarial networks (GANs) are powerful tools for learning g...
research
03/01/2021

On the Fairness of Generative Adversarial Networks (GANs)

Generative adversarial networks (GANs) are one of the greatest advances ...
research
01/07/2021

A spin-glass model for the loss surfaces of generative adversarial networks

We present a novel mathematical model that seeks to capture the key desi...
research
09/05/2022

Dynamics of Fourier Modes in Torus Generative Adversarial Networks

Generative Adversarial Networks (GANs) are powerful Machine Learning mod...
research
11/13/2018

Evaluating GANs via Duality

Generative Adversarial Networks (GANs) have shown great results in accur...
research
03/21/2018

Some Theoretical Properties of GANs

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

Please sign up or login with your details

Forgot password? Click here to reset