Machine learning of discrete field theories with guaranteed convergence and uncertainty quantification
Preprint
Abstract
We introduce a method based on Gaussian process regression to identify discrete variational principles from observed solutions of a field theory. The method is based on the data-based identification of a discrete Lagrangian density. It is a geometric machine learning technique in the sense that the variational structure of the true field theory is reflected in the data-driven model by design. We provide a rigorous convergence statement of the method. The proof circumvents challenges posed by the ambiguity of discrete Lagrangian densities in the inverse problem of variational calculus. Moreover, our method can be used to quantify model uncertainty in the equations of motions and any linear observable of the discrete field theory. This is illustrated on the example of the discrete wave equation and Schrödinger equation. The article constitutes an extension of our previous article arXiv:2404.19626 for the data-driven identification of (discrete) Lagrangians for variational dynamics from an ode setting to the setting of discrete pdes.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifoldsComputer Methods in Applied Mechanics and Engineering, 2023
- Learning Discrete Lagrangians for Variational PDEs from Data and Detection of Travelling Waves2023
- Variational learning of Euler–Lagrange dynamics from dataJournal of Computational and Applied Mathematics, 2022
- Calculus of Variations2015
- Functional Analysis, Sobolev Spaces and Partial Differential Equations2011
- Kernels and Reproducing Kernel Hilbert Spaces2008
- Multisymplectic Geometry, Variational Integrators, and Nonlinear PDEsCommunications in Mathematical Physics, 1998
- On the inverse problem with symmetries, and the appearance of cohomologies in classical Lagrangian dynamicsReports on Mathematical Physics, 1989
- Об единственности Лагранжева описания заряженных частиц во внешнем магнитном полеIl Nuovo Cimento A (1971-1996), 1987
- Equations of motion, commutation relations and ambiguities in the Lagrangian formalismAnnals of Physics, 1982