美文网首页
The Numerics of GANs

The Numerics of GANs

作者: 朱小虎XiaohuZhu | 来源:发表于2017-10-07 13:05 被阅读144次

    https://arxiv.org/pdf/1705.10461.pdf

    In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives.

    Our findings suggest that the convergence of current algorithms suffers due to two factors:

    • presence of eigenvalues of the Jacobian of the gradient vector field with zero real-part,
    • eigenvalues with big imaginary part.

    Using these findings, we design a new algorithm that overcomes some of these limitations and has better convergence properties.

    Experimentally, we demonstrate its superiority on training common GAN architectures and show convergence on GAN architectures that are known to be notoriously hard to train.

    相关文章

      网友评论

          本文标题:The Numerics of GANs

          本文链接:https://www.haomeiwen.com/subject/ttrjyxtx.html