We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs. To justify the usage of neural networks, we prove that they are universal approximators of transport plans between probability distributions. We evaluate the performance of our optimal transport algorithm on toy examples and on the unpaired image-to-image style translation task.
翻译:我们提出了一个基于神经网络的新型算法,用于计算最佳运输地图和强力和弱力运输成本计划。为了证明使用神经网络是合理的,我们证明这些算法是概率分布之间运输计划的通用近似方。我们评估了我们最佳运输算法在玩具例子和未受保护的图像到图像风格翻译任务方面的表现。