A game-theoretic approach for Generative Adversarial Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Franci, Barbara, Grammatico, Sergio
Format: Preprint
Publié: 2020
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918112724516864
author Franci, Barbara
Grammatico, Sergio
author_facet Franci, Barbara
Grammatico, Sergio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2003_13637
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle A game-theoretic approach for Generative Adversarial Networks
Franci, Barbara
Grammatico, Sergio
Machine Learning
Computer Science and Game Theory
Optimization and Control
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.
title A game-theoretic approach for Generative Adversarial Networks
topic Machine Learning
Computer Science and Game Theory
Optimization and Control
url https://arxiv.org/abs/2003.13637