用赫尔姆霍兹度量检测神经ODE是否符合物理规律,可直接学习拉格朗日方程。
Lagrangian neural ODEs: Measuring the existence of a Lagrangian with Helmholtz metrics
- 引入赫尔姆霍兹度量衡量常微分方程与拉格朗日系统的相似性
- 在含噪系统上验证,仅用位置数据即可区分拉格朗日与非拉格朗日系统
- 构建拉格朗日神经ODE,训练与推理零成本,提升物理一致性
神经常微分方程是物理建模中广泛使用的强大机器学习技术,但并非所有解都对应于物理上合理的欧拉-拉格朗日方程。本文提出赫尔姆霍兹度量来量化给定常微分方程与拉格朗日系统的接近程度,并在多个基础物理系统(含噪声)上验证其有效性。通过将该度量与二阶神经ODE结合,构建了拉格朗日神经ODE,可直接学习满足欧拉-拉格朗日方程的动态系统,且训练和推理无需额外开销。实验表明,仅使用位置数据,该方法能有效区分拉格朗日与非拉格朗日系统,并显著提升神经ODE的物理合理性。
原文摘要 · Abstract (English)
Neural ODEs are a widely used, powerful machine learning technique in particular for physics. However, not every solution is physical in that it is an Euler-Lagrange equation. We present Helmholtz metrics to quantify this resemblance for a given ODE and demonstrate their capabilities on several fundamental systems with noise. We combine them with a second order neural ODE to form a Lagrangian neural ODE, which allows to learn Euler-Lagrange equations in a direct fashion and with zero additional inference cost. We demonstrate that, using only positional data, they can distinguish Lagrangian and non-Lagrangian systems and improve the neural ODE solutions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。