arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08249cs.LGmath.OCstat.ML
收藏

正则化最优传输训练GANs的收敛性和鲁棒性

On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

University of Southern California(南加州大学);University of Toronto(多伦多大学)

Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee

摘要:

生成对抗网络(GANs)是学习数据分布的最实用的方法之一。流行的GAN公式是基于使用Wasserstein距离作为概率分布之间的度量。不幸的是,最小化数据分布和生成模型分布之间的Wasserstein距离是一个计算上具有挑战性的问题,因为其目标是非凸的,非光滑的,甚至难以计算。在这项工作中,我们表明,获得梯度信息的平滑Wasserstein GAN制定,这是基于正则化的最优运输(OT),是计算上毫不费力,因此可以应用一阶优化方法,以尽量减少这一目标。因此,我们建立了理论上的收敛保证平稳的一类建议的GAN优化算法。与原来的非光滑配方,我们的算法只需要解决的最优近似。我们应用我们的方法学习MNIST数字以及CIFAR-10图像。我们的实验表明,我们的方法是计算效率和生成图像的最先进的算法给出相同的架构和计算能力。

英文摘要:

Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions. Unfortunately, minimizing the Wasserstein distance between the data distribution and the generative model distribution is a computationally challenging problem as its objective is non-convex, non-smooth, and even hard to compute. In this work, we show that obtaining gradient information of the smoothed Wasserstein GAN formulation, which is based on regularized Optimal Transport (OT), is computationally effortless and hence one can apply first order optimization methods to minimize this objective. Consequently, we establish theoretical convergence guarantee to stationarity for a proposed class of GAN optimization algorithms. Unlike the original non-smooth formulation, our algorithm only requires solving the discriminator to approximate optimality. We apply our method to learning MNIST digits as well as CIFAR-10images. Our experiments show that our method is computationally efficient and generates images comparable to the state of the art algorithms given the same architecture and computational power.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑