Stochastic differential equation approximations of generative adversarial network training and its long-run behavior.
In: Journal of Applied Probability, Jg. 61 (2024-06-01), Heft 2, S. 465-489
Online
academicJournal
Zugriff:
This paper analyzes the training process of generative adversarial networks (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 GAN training via the invariant measures of its SDE approximations under proper conditions. This work builds a theoretical foundation for GAN training and provides analytical tools to study its evolution and stability. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Applied Probability is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
Stochastic differential equation approximations of generative adversarial network training and its long-run behavior.
|
---|---|
Autor/in / Beteiligte Person: | Cao, Haoyang ; Guo, Xin |
Link: | |
Zeitschrift: | Journal of Applied Probability, Jg. 61 (2024-06-01), Heft 2, S. 465-489 |
Veröffentlichung: | 2024 |
Medientyp: | academicJournal |
ISSN: | 0021-9002 (print) |
DOI: | 10.1017/jpr.2023.57 |
Schlagwort: |
|
Sonstiges: |
|