The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
arXiv:2103.11488
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 grid error is bounded by the sum of and the network approximation error, where is the time step size and is the local truncation error order. Numerical results of several physically relevant examples are provided to demonstrate our theory.
References in corpus (11)
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- Deep Network Approximation for Smooth Functions
- Neural Network Approximation: Three Hidden Layers Are Enough
- Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
- Towards Understanding the Spectral Bias of Deep Learning
- Deep Network with Approximation Error Being Reciprocal of Width to Power of Square Root of Depth
- Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
- A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations
- How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?
- On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
- FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods