TL;DR本研究提出了可至少连续二阶可微且双 Lipschitz 连续的非均匀 B 样条流,它具有解析反演变换,并应用于解决 Boltzmann 生成器中的力匹配问题,其结果比以前的样条流更好,比平滑归一化流更快。
Abstract
normalizing flows have been successfully modeling a complex probability
distribution as an invertible transformation of a simple base distribution.
However, there are often applications that require more than invertibility. For
instance, the computation of energies and forces in physic