arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04100cs.LG
收藏

基于物理引导的线性微分方程解算子学习的数据增强

Physics-guided Data Augmentation for Learning the Solution Operator of Linear Differential Equations

Nanjing University of Aeronautics and Astronautics(南京航空航天大学)

Ye Li, Yiwen Pang, Bin Shan

摘要:

神经网络,特别是最近提出的神经算子模型,越来越多地被用来寻找微分方程的解算子。与传统的数值求解器相比,它们在实际应用中速度更快,效率更高。然而,一个关键问题是训练神经算子模型需要大量的地面真实数据,这些数据通常来自缓慢的数值求解器。在本文中,我们提出了一个物理指导的数据增强(PGDA)方法,以提高神经算子模型的准确性和泛化能力。训练数据通过微分方程的物理性质(例如线性和平移)自然地增加。我们证明了PGDA的优势,对各种线性微分方程,PGDA可以提高样本的复杂性,是强大的分布移位。

英文摘要:

Neural networks, especially the recent proposed neural operator models, are increasingly being used to find the solution operator of differential equations. Compared to traditional numerical solvers, they are much faster and more efficient in practical applications. However, one critical issue is that training neural operator models require large amount of ground truth data, which usually comes from the slow numerical solvers. In this paper, we propose a physics-guided data augmentation (PGDA) method to improve the accuracy and generalization of neural operator models. Training data is augmented naturally through the physical properties of differential equations such as linearity and translation. We demonstrate the advantage of PGDA on a variety of linear differential equations, showing that PGDA can improve the sample complexity and is robust to distributional shift.

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。

↑