A game-theoretic approach for Generative Adversarial Networks

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Generative adversarial networks (GANs) are a class of generative models, known for producing accurate samples. The key feature of GANs is that there are two antagonistic neural networks: the generator and the discriminator. The main bottleneck for their implementation is that the neural networks are very hard to train. One way to improve their performance is to design reliable algorithms for the adversarial process. Since the training can be cast as a stochastic Nash equilibrium problem, we rewrite it as a variational inequality and introduce an algorithm to compute an approximate solution. Specifically, we propose a stochastic relaxed forward-backward algorithm for GANs. We prove that when the pseudogradient mapping of the game is monotone, we have convergence to an exact solution or in a neighbourhood of it.

Original languageEnglish
Title of host publicationProceedings of the 59th IEEE Conference on Decision and Control, CDC 2020
Place of PublicationPiscataway, NJ, USA
PublisherIEEE
Pages1646-1651
ISBN (Electronic)978-1-7281-7447-1
DOIs
Publication statusPublished - 2020
Event59th IEEE Conference on Decision and Control, CDC 2020 - Virtual, Jeju Island, Korea, Republic of
Duration: 14 Dec 202018 Dec 2020

Conference

Conference59th IEEE Conference on Decision and Control, CDC 2020
CountryKorea, Republic of
CityVirtual, Jeju Island
Period14/12/2018/12/20

Fingerprint Dive into the research topics of 'A game-theoretic approach for Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this