BriefGPT.xyz
Oct, 2018
使用生成对抗网络的可伸缩非平衡最优输运
Scalable Unbalanced Optimal Transport using Generative Adversarial Networks
HTML
PDF
Karren D. Yang, Caroline Uhler
TL;DR
本文介绍一种基于生成对抗网络的可伸缩的非平衡优化输运方法，该方法可以同时学习输运映射和缩放因子，以最优的代价推动源测量到目标测量，并提供了理论证明和数值实验。
Abstract
generative adversarial networks
(GANs) are an expressive class of
neural generative models
with tremendous success in modeling high-dimensional continuous measures. In this paper, we present a scalable method for
→