arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.01741cs.LG
收藏

神经守恒定律:无发散的观点

Neural Conservation Laws: A Divergence-Free Perspective

Vector Institute(向量研究所);Meta AI

Jack Richter-Powell, Yaron Lipman, Ricky T. Q. Chen

摘要:

我们研究深度神经网络的参数化,通过设计满足连续性方程,一个基本的守恒定律。这是通过观察连续性方程的任何解都可以表示为无发散向量场来实现的。因此,我们提出了通过微分形式的概念来构建无发散神经网络,并在自动微分的帮助下,实现了两个实际的结构。因此,我们可以参数化总是精确满足连续性方程的密度和向量场对,而不需要额外的惩罚方法或昂贵的数值模拟。此外,我们证明了这些模型是通用的,因此可以用来表示任何发散自由向量场。最后,我们通过计算基于神经网络的流体方程的解决方案,求解霍奇分解,并学习动态最优传输映射实验验证我们的方法。

英文摘要:

We investigate the parameterization of deep neural networks that by design satisfy the continuity equation, a fundamental conservation law. This is enabled by the observation that any solution of the continuity equation can be represented as a divergence-free vector field. We hence propose building divergence-free neural networks through the concept of differential forms, and with the aid of automatic differentiation, realize two practical constructions. As a result, we can parameterize pairs of densities and vector fields that always exactly satisfy the continuity equation, foregoing the need for extra penalty methods or expensive numerical simulation. Furthermore, we prove these models are universal and so can be used to represent any divergence-free vector field. Finally, we experimentally validate our approaches by computing neural network-based solutions to fluid equations, solving for the Hodge decomposition, and learning dynamical optimal transport maps.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑