BriefGPT.xyz
Jan, 2022
神经最优传输
Neural Optimal Transport
HTML
PDF
Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
TL;DR
该研究介绍了一种基于神经网络的算法，用于计算强和弱输运成本的最优输运图和计划，并证明了神经网络是概率分布之间传输计划的通用逼近器。通过在玩具示例和非成对图像翻译上评估我们的最优输运算法的性能。
Abstract
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
→