Saved in:
Bibliographic Details
Main Authors: Djehiche, Boualem, Tembine, Hamidou
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.12321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916151580164096
author Djehiche, Boualem
Tembine, Hamidou
author_facet Djehiche, Boualem
Tembine, Hamidou
contents In this article we show that the asymptotic outcomes of both shallow and deep neural networks such as those used in BloombergGPT to generate economic time series are exactly the Nash equilibria of a non-potential game. We then design and analyze deep neural network algorithms that converge to these equilibria. The methodology is extended to federated deep neural networks between clusters of regional servers and on-device clients. Finally, the variational inequalities behind large language models including encoder-decoder related transformers are established.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12321
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The outcomes of generative AI are exactly the Nash equilibria of a non-potential game
Djehiche, Boualem
Tembine, Hamidou
Computer Science and Game Theory
In this article we show that the asymptotic outcomes of both shallow and deep neural networks such as those used in BloombergGPT to generate economic time series are exactly the Nash equilibria of a non-potential game. We then design and analyze deep neural network algorithms that converge to these equilibria. The methodology is extended to federated deep neural networks between clusters of regional servers and on-device clients. Finally, the variational inequalities behind large language models including encoder-decoder related transformers are established.
title The outcomes of generative AI are exactly the Nash equilibria of a non-potential game
topic Computer Science and Game Theory
url https://arxiv.org/abs/2401.12321