We propose a stable method to train Wasserstein generative adversarial networks. In order to enhance stability, we consider two objective functions using the $c$-transform based on Kantorovich duality which arises in the theory of optimal transport. We experimentally show that this algorithm can effectively enforce the Lipschitz constraint on the discriminator while other standard methods fail to do so. As a consequence, our method yields an accurate estimation for the optimal discriminator and also for the Wasserstein distance between the true distribution and the generated one. Our method requires no gradient penalties nor corresponding hyperparameter tuning and is computationally more efficient than other methods. At the same time, it yields competitive generators of synthetic images based on the MNIST, F-MNIST, and CIFAR-10 datasets.
翻译:我们提出一个稳定的方法来培训瓦塞斯坦基因对抗网络。为了增强稳定性,我们考虑使用基于康托罗维奇双轨制的基于康托罗维奇双轨制的两个客观功能,这是在最佳运输理论中产生的。我们实验性地表明,这种算法可以有效地对歧视者实施利普施茨限制,而其他标准方法却未能这样做。因此,我们的方法得出了对最佳歧视者以及真正分布和生成的瓦塞斯坦距离的准确估计。我们的方法不需要梯度罚款或相应的超分光计调整,而且比其他方法更有效率。与此同时,它产生有竞争力的合成图像生成者,这些图像以MNIST、F-MNIST和CIFAR-10数据集为基础。