Abstract
Neural solvers for partial differential equations (PDEs) can approach an accurate solution while their parameters grow without bound. In such cases, the limiting solution may have no finite representation in the chosen model, leaving the best loss unattained. Our analysis connects missing limits in deep neural tanh- networks to unbounded hidden parameters or increasingly redundant neurons. For a class of models built from translated kernels, we describe the missing functions and recover them by adding kernel derivatives to the model. This completion makes the best approximation attainable under standard assumptions. Numerical studies follow the associated parameter growth and explore how completion affects PDE optimization.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Fernández, D. (2026). Singular parameters and missing limits in neural PDE solvers. https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers
MLA 9
Fernández, Daniel. "Singular parameters and missing limits in neural PDE solvers." https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers.
Chicago (author–date)
Fernández, Daniel. 2026. "Singular parameters and missing limits in neural PDE solvers." https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers.
Harvard
Fernández, D. (2026) 'Singular parameters and missing limits in neural PDE solvers', Available at: https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers.
Vancouver
Fernández D. Singular parameters and missing limits in neural PDE solvers. https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers
IEEE
D. Fernández, "Singular parameters and missing limits in neural PDE solvers," https://omanscience.com/en/articles/singular-parameters-and-missing-limits-in-neural-pde-solvers.