On the limitations of first-order approximation in GAN dynamics
© Copyright 2018 by the author(s). While Generative Adversarial Networks (GANs) have demonstrated promising performance on multiple vision tasks, their learning dynamics are not yet well understood, both in theory and in practice. To address this issue, we study GAN dynamics in a simple yet rich par...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
2021-11-08T19:08:11Z.
|
Subjects: | |
Online Access: | Get fulltext |