papers AI Learner
The Github is limit! Click to go to the new site.

Training GANs with Centripetal Acceleration

2019-02-24
Wei Peng, Yuhong Dai, Hui Zhang, Lizhi Cheng

Abstract

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. 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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1902.08949

PDF

https://arxiv.org/pdf/1902.08949


Similar Posts

Comments