The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
This work addresses the challenge of error analysis for dynamics discovery methods, offering incremental theoretical insights for researchers in computational science and machine learning.
The paper tackles the problem of identifying hidden dynamics from observed data by combining linear multistep methods (LMMs) with deep learning, providing error estimates that show the ℓ² grid error is bounded by O(h^p) plus network approximation error, with numerical examples validating the theory.
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 $\ell^2$ grid error is bounded by the sum of $O(h^p)$ and the network approximation error, where $h$ is the time step size and $p$ is the local truncation error order. Numerical results of several physically relevant examples are provided to demonstrate our theory.