Saved in:
Bibliographic Details
Main Authors: Cao, Haoyang, Guo, Xin
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2006.02047
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914047504416768
author Cao, Haoyang
Guo, Xin
author_facet Cao, Haoyang
Guo, Xin
contents This paper analyzes the training process of GANs via stochastic differential equations (SDEs). It first establishes SDE approximations for the training of GANs under stochastic gradient algorithms, with precise error bound analysis. It then describes the long-run behavior of GANs training via the invariant measures of its SDE approximations under proper conditions. This work builds theoretical foundation for GANs training and provides analytical tools to study its evolution and stability.
format Preprint
id arxiv_https___arxiv_org_abs_2006_02047
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle SDE approximations of GANs training and its long-run behavior
Cao, Haoyang
Guo, Xin
Machine Learning
Probability
This paper analyzes the training process of GANs via stochastic differential equations (SDEs). It first establishes SDE approximations for the training of GANs under stochastic gradient algorithms, with precise error bound analysis. It then describes the long-run behavior of GANs training via the invariant measures of its SDE approximations under proper conditions. This work builds theoretical foundation for GANs training and provides analytical tools to study its evolution and stability.
title SDE approximations of GANs training and its long-run behavior
topic Machine Learning
Probability
url https://arxiv.org/abs/2006.02047