提出对抗最优传输正则化学习混沌系统模拟器

1. 12:00
   arXiv · Statistics Machine Learning

   Learning to Emulate Chaos：对抗最优传输正则化

   论文提出一族对抗最优传输目标，能从单条含噪轨迹联合学习高质量统计量与物理一致的混沌系统仿真器。方法给出 Sinkhorn 散度（2-Wasserstein）与 WGAN 式对偶（1-Wasserstein）两种形式化并做理论分析。在含高维时空混沌的多类系统实验中，训练所得仿真器的长期统计保真度显著提升。

Current heat 9·Comparable peak 10（Oct 9）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.