We know SGAN may have a risk of gradient vanishing. A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing. Is there any GAN having no gradient vanishing and no 1-Lipschitz constraint on discriminator? We do find one, called GAN-QP. To construct a new framework of Generative Adversarial Network (GAN) usually includes three steps: 1. choose a probability divergence; 2. convert it into a dual form; 3. play a min-max game. In this articles, we demonstrate that the first step is not necessary. We can analyse the property of divergence and even construct new divergence in dual space directly. As a reward, we obtain a simpler alternative of WGAN: GAN-QP. We demonstrate that GAN-QP have a better performance than WGAN in theory and practice.
翻译:我们知道SGAN可能有渐变消失的危险。 在对歧视者实行1-利普施茨限制以防止梯度消失的帮助下,WGAN是一个显著的改进。是否有任何GAN没有梯度消失,对歧视者没有1-利普施茨限制?我们确实找到了一个称为GAN-QP的GAN-QP。建立一个新的基因反转网络(GAN)框架通常包括三个步骤:1.选择概率差异;2.将它转换成一种双重形式;3.玩一个微积分游戏。我们在这篇文章中证明第一步是不必要的。我们可以直接分析分歧的属性,甚至直接在双重空间中建立新的差异。作为奖励,我们得到了一个更简单的WGAN:GAN-QP的替代。我们证明GAN-QP在理论和实践上比WGAN有更好的表现。