用强化学习动态调学习率，让GAN训练更稳定
Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN
- 用智能代理控制步长，实现快慢协同优化
- 在三个基准数据集上显著降低训练震荡，提升收敛性
- 适合对训练稳定性要求高的GAN应用开发者
目前典型生成对抗网络（GAN）的训练过程仍对数据特性和超参数高度敏感，尤其当训练集方差较大时，易出现严重振荡、难以收敛甚至完全无法收敛的问题。为此，本文提出一种新型智能优化器——快慢协同优化器（FSCO），通过在训练过程中引入强化学习，使训练步长由智能体控制，从而提升训练稳定性。该方法采用可变学习率机制，使GAN对步长变化不敏感。在三个基准数据集上的实验验证了FSCO的有效性。
原文摘要 · Abstract (English)
Up to now, the training processes of typical Generative Adversarial Networks (GANs) are still particularly sensitive to data properties and hyperparameters, which may lead to severe oscillations, difficulties in convergence, or even failures to converge, especially when the overall variances of the training sets are large. These phenomena are often attributed to the training characteristics of such networks. Aiming at the problem, this paper develops a new intelligent optimizer, Fast-Slow Co-advancing Optimizer (FSCO), which employs reinforcement learning in the training process of GANs to make training easier. Specifically, this paper allows the training step size to be controlled by an agent to improve training stability, and makes the training process more intelligent with variable learning rates, making GANs less sensitive to step size. Experiments have been conducted on three benchmark datasets to verify the effectiveness of the developed FSCO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。