An adaptive Galerkin neural-network method for minimum-norm control of wave equations
Abstract
We develop an adaptive Galerkin neural-network method for computing minimum-L2-norm interior controls for wave equations with spatially varying coefficients. Within the Hilbert Uniqueness Method, adjoint waves are approximated directly in space-time by least-squares Galerkin projections onto trial spaces enriched by neural-network basis functions selected through residual-based training. Linear Galerkin solves determine the adjoint approximations, and a separate linear system reconstructs the control. The least-squares objective provides an indicator for adaptive enrichment and stopping; the experiments use a Ritz-based terminal-data version whose continuous-error interpretation additionally requires an eigenpair consistency estimate. The main difficulty is that adjoint errors perturb this reconstruction system. Assuming observability of the continuous equation, we derive sufficient stability conditions involving a worst-case factor √n multiplying the maximal adjoint error, where n is the number of retained terminal modes. A fully discrete error estimate separates terminal-space truncation, adjoint approximation, and assembly errors, yielding convergence to the minimum-norm control when the truncation error, the √n-weighted adjoint error, and the assembly errors tend to zero as n grows. For spectral terminal bases, additional regularity and uniform contraction assumptions yield quantitative convergence rates and show that O(log n) accepted enrichment steps per mode suffice to balance the neural and truncation errors. Numerical experiments on a nonconvex Cassini oval, a square containing a low-speed lens, and a three-dimensional ball with a graded coefficient illustrate the method.
Related
- An Adaptive Transferable Neural Network for Partial Differential Equations with Anisotropic or Sharp Solutions
- High-order L2-Galerkin schemes for the decoupled potential integral equations
- Adaptive Multilevel Discontinuous Galerkin Methods on GPUs
- Flux-Matched Poisson Iteration for Generated Jacobian Equations: Local Convergence and Spectral Galerkin Approximation
- Preconditioning for the time-dependent Stokes equations: stage-weighted Radau IIA and weighted discontinuous Galerkin time-stepping
BibTeX
@misc{hien2026adaptive,
title = {{An adaptive Galerkin neural-network method for minimum-norm control of wave equations}},
author = {Nguyen Gia Hien},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.15220},
eprint = {2610.15220},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.15220},
}
RIS
TY - UNPB
TI - An adaptive Galerkin neural-network method for minimum-norm control of wave equations
AU - Nguyen Gia Hien
PY - 2026
DA - 2026/10/10
PB - arXiv
DO - 10.48550/arxiv.2610.15220
UR - https://arxiv.org/abs/2610.15220
AB - We develop an adaptive Galerkin neural-network method for computing minimum-L^2-norm interior controls for wave equations with spatially varying coefficients. Within the Hilbert Uniqueness Method, adjoint waves are approximated directly in space-time by least-squares Galerkin projections onto trial spaces enriched by neural-network basis functions selected through residual-based training. Linear Galerkin solves determine the adjoint approximations, and a separate linear system reconstructs the control. The least-squares objective provides an indicator for adaptive enrichment and stopping; the experiments use a Ritz-based terminal-data version whose continuous-error interpretation additionally requires an eigenpair consistency estimate. The main difficulty is that adjoint errors perturb this reconstruction system. Assuming observability of the continuous equation, we derive sufficient stability conditions involving a worst-case factor √n multiplying the maximal adjoint error, where n is the number of retained terminal modes. A fully discrete error estimate separates terminal-space truncation, adjoint approximation, and assembly errors, yielding convergence to the minimum-norm control when the truncation error, the √n-weighted adjoint error, and the assembly errors tend to zero as n grows. For spectral terminal bases, additional regularity and uniform contraction assumptions yield quantitative convergence rates and show that O(log n) accepted enrichment steps per mode suffice to balance the neural and truncation errors. Numerical experiments on a nonconvex Cassini oval, a square containing a low-speed lens, and a three-dimensional ball with a graded coefficient illustrate the method.
ER -