Oliehoek, F., Savani, R., Gallego, J. et al. (2 more authors) (2019) Beyond local Nash equilibria for adversarial networks. In: Atzmueller, M. and Duivesteijn, W., (eds.) Proceedings of the 30th Benelux Conference on Artificial Intelligence (BNAIC 2018). 30th Benelux Conference on Artificial Intelligence, BNAIC 2018, 08-09 Nov 2018, ‘s-Hertogenbosch, Netherlands. Communications in Computer and Information Science, 1021 . Springer , pp. 73-89. ISBN 9783030319779
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.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2018 Springer. This is an author-produced version of a paper subsequently published in Atzmueller M., Duivesteijn W. (eds) Artificial Intelligence. BNAIC 2018. Communications in Computer and Information Science. Uploaded in accordance with the publisher's self-archiving policy. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 12 Dec 2018 12:55 |
Last Modified: | 23 Dec 2019 10:50 |
Status: | Published |
Publisher: | Springer |
Series Name: | Communications in Computer and Information Science |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-030-31978-6_7 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:139768 |