Training generative adversarial networks (GANs) often suffers from cyclic behaviours of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the centre of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviours. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.

训练生成对抗网络（GAN）通常会遭受迭代器的循环行为。基于一个简单的直觉，即以匀速圆周运动的物体向心加速度的方向朝向圆心，我们提出了同时向心加速度（SCA）方法和交替向心加速度（ACA）方法来减轻循环行为。在适当的条件下，对于双线性博弈，使用SCA或ACA的梯度下降方法被证明是线性收敛的。通过在GAN设置场景中将ACA应用于现有的基于梯度的算法进行了数值实验，证明了ACA的优越性。