English

The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation

Numerical Analysis 2022-09-14 v2 Machine Learning Numerical Analysis

Abstract

Identifying hidden dynamics from observed data is a significant and challenging task in a wide range of applications. Recently, the combination of linear multistep methods (LMMs) and deep learning has been successfully employed to discover dynamics, whereas a complete convergence analysis of this approach is still under development. In this work, we consider the deep network-based LMMs for the discovery of dynamics. We put forward error estimates for these methods using the approximation property of deep networks. It indicates, for certain families of LMMs, that the 2\ell^2 grid error is bounded by the sum of O(hp)O(h^p) and the network approximation error, where hh is the time step size and pp is the local truncation error order. Numerical results of several physically relevant examples are provided to demonstrate our theory.

Keywords

Cite

@article{arxiv.2103.11488,
  title  = {The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation},
  author = {Qiang Du and Yiqi Gu and Haizhao Yang and Chao Zhou},
  journal= {arXiv preprint arXiv:2103.11488},
  year   = {2022}
}
R2 v1 2026-06-24T00:24:08.002Z