Metraipolis › archive › dc_fd4ed08680a7

Computing high-order mixed derivatives in physics-informed neural networks using multi-index Bell polynomials — arXiv:2609.03768

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03768
License (as archived)
CC0-1.0
Archived
2026-10-17T03:07:58.925Z
SHA-256 of the archived text
13672f11213504040b887325a5a16dc6f29ffc8d1c45bbd97a104fbf146cf165
Stable URL of this page
https://metraipolis.com/documento/dc_fd4ed08680a7

How to cite

Computing high-order mixed derivatives in physics-informed neural networks using multi-index Bell polynomials — arXiv:2609.03768 — arXiv (en), https://arxiv.org/abs/2609.03768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd4ed08680a7 (Metraipolis archive dc_fd4ed08680a7, sha256 13672f11213504040b887325a5a16dc6f29ffc8d1c45bbd97a104fbf146cf165)
BibTeX
@misc{dcfd4ed08680a7,
  title = {Computing high-order mixed derivatives in physics-informed neural networks using multi-index Bell polynomials — arXiv:2609.03768},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03768},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd4ed08680a7; sha256 13672f11213504040b887325a5a16dc6f29ffc8d1c45bbd97a104fbf146cf165},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-informed neural networks for high-order partial differential equations require mixed input derivatives and their gradients with respect to the network parameters. Standard implementations obtain an order-$K$ derivative by repeated automatic differentiation. We instead organize the forward recursion of the multivariate Faà di Bruno formula and its explicit backpropagation over a prescribed downward-closed set of multi-indices, with the Bell-polynomial convolutions tabulated once. The forward pass carries only the derivatives the differential operator requires. The backward pass propagates gradients from losses formed from any subset of them, including nonlinear products and coupled fields. Both recursions are exact up to roundoff and avoid nested computational graphs. An independent Taylor-jet implementation, symbolic checks of the test problems, and finite differences verify derivatives and loss gradients through order seven. On one CPU core, the method evaluates 330 mixed derivatives with respect to four inputs through order seven and the corresponding loss gradient without the memory failures observed for several nested implementations. Numerical tests include third-, fifth-, and seventh-order dispersive equations, incompressible flow, and a manufactured five-field electrohydrodynamic system. The seventh-order Zakharov-Kuznetsov test in $3+1$ dimensions has a relative solution error of $6\times10^{-4}$.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-04 in physics.comp-ph).
Categorie arXiv: Computational Physics (physics.comp-ph) ; Plasma Physics (physics.plasm-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.03768 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:00:43.886Z dalla pagina https://arxiv.org/catchup/physics.comp-ph/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).