论文标题
一种逃避训练中极限周期的方法
A method for escaping limit cycles in training GANs
论文作者
论文摘要
本文主要进行进一步的研究，以减轻训练生成对抗网络（GAN）中的极限自行车行为问题，这是通过拟议的预测性中心加速算法（PCAA）。具体而言，我们首先在一般双线性游戏的PCAA的最后近期收敛速率上得出了上限和下限，其上限显着改善了先前的结果。然后，我们将PCAA与自适应力矩估计算法（ADAM）相结合，以提出PCAA-ADAM，这是一种用于训练gan的实用方法。最后，我们分别通过双线性游戏，多元高斯分布和Celeba数据集进行了实验来验证所提出的算法的有效性。
This paper mainly conducts further research to alleviate the issue of limit cycling behavior in training generative adversarial networks (GANs) through the proposed predictive centripetal acceleration algorithm (PCAA). Specifically, we first derive the upper and lower bounds on the last-iterate convergence rates of PCAA for the general bilinear game, with the upper bound notably improving upon previous results. Then, we combine PCAA with the adaptive moment estimation algorithm (Adam) to propose PCAA-Adam, a practical approach for training GANs. Finally, we validate the effectiveness of the proposed algorithm through experiments conducted on bilinear games, multivariate Gaussian distributions, and the CelebA dataset, respectively.
