Beyond Local Nash Equilibria for Adversarial Networks

Frans A. Oliehoek*, Rahul Savani, Jose Gallego, Elise van der Pol, Roderich Groß

*Corresponding author for this work

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

8 Citations (Scopus)
127 Downloads (Pure)

Abstract

Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a ‘local Nash equilibrium’ (LNE). Such LNEs, however, can be arbitrarily far from an actual Nash equilibrium (NE), which implies that there are no guarantees on the quality of the found generator or classifier. This paper proposes to model GANs explicitly as finite games in mixed strategies, thereby ensuring that every LNE is an NE. We use the Parallel Nash Memory as a solution method, which is proven to monotonically converge to a resource-bounded Nash equilibrium. We empirically demonstrate that our method is less prone to typical GAN problems such as mode collapse and produces solutions that are less exploitable than those produced by GANs and MGANs.

Original languageEnglish
Title of host publicationArtificial Intelligence
Subtitle of host publication30th Benelux Conference, BNAIC 2018, Revised Selected Papers
EditorsMartin Atzmueller, Wouter Duivesteijn
Place of PublicationCham
PublisherSpringer
Pages73-89
Number of pages17
ISBN (Electronic)978-3-030-31978-6
ISBN (Print)978-3-030-31977-9
DOIs
Publication statusPublished - 2019
Event30th Benelux Conference on Artificial Intelligence, BNAIC 2018 - ‘s-Hertogenbosch, Netherlands
Duration: 8 Nov 20189 Nov 2018

Publication series

NameCommunications in Computer and Information Science
Volume1021
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th Benelux Conference on Artificial Intelligence, BNAIC 2018
Country/TerritoryNetherlands
City‘s-Hertogenbosch
Period8/11/189/11/18

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
 
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Fingerprint

Dive into the research topics of 'Beyond Local Nash Equilibria for Adversarial Networks'. Together they form a unique fingerprint.

Cite this