Beyond Local Nash Equilibria for Adversarial Networks

Oliehoek, Frans A, Savani, Rahul ORCID: 0000-0003-1262-7831, Gallego, Jose, van der Pol, Elise and Groß, Roderich (2019) Beyond Local Nash Equilibria for Adversarial Networks .

PDF Oliehoek19BNAIC_pp.pdf - Author Accepted Manuscript Download (1MB) | Preview

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.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	38 Economics, 3803 Economic Theory, Liver Disease, Hepatitis, Digestive Diseases
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	22 Nov 2024 08:57
Last Modified:	29 May 2026 19:38
DOI:	10.1007/978-3-030-31978-6_7
Related Websites:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3188821
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.