Metraipolis › archive › dc_10e36c8d6bd0

FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial… — arXiv:2610.08016

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08016
License (as archived)
CC0-1.0
Archived
2026-10-07T11:42:44.466Z
SHA-256 of the archived text
7e0dab10c562ff0c9be5f89d54f10fdff42d7c0d38bdd3bc6c4a0ba5b33884b6
Stable URL of this page
https://metraipolis.com/documento/dc_10e36c8d6bd0

How to cite

FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial… — arXiv:2610.08016 — arXiv (en), https://arxiv.org/abs/2610.08016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10e36c8d6bd0 (Metraipolis archive dc_10e36c8d6bd0, sha256 7e0dab10c562ff0c9be5f89d54f10fdff42d7c0d38bdd3bc6c4a0ba5b33884b6)
BibTeX
@misc{dc10e36c8d6bd0,
  title = {FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial… — arXiv:2610.08016},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08016},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10e36c8d6bd0; sha256 7e0dab10c562ff0c9be5f89d54f10fdff42d7c0d38bdd3bc6c4a0ba5b33884b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We construct neural approximation classes native to the graph spaces H(div) and H(curl), in two and three dimensions and, for H(div), in any dimension. Every realization lies in the space for all parameter values, and with kinked potentials, such as ReLU networks, the admissible jumps appear at finite width. The classes are images of scalar and componentwise networks under fixed operators of the de Rham complex, and do not involve a mesh or finite element emulation. For H(div) in R^n two native classes are given on an equal footing, with a skew-symmetric potential $A$: $\mathrm{Div}\,A+R_nq+\mathbf{h}$, with the divergence $q$ as an explicit unknown, and $\mathrm{Div}\,A+\mathbf{z}$ with an $H^1$ field $\mathbf{z}$; for H(curl) the analogous classes are $\mathrm{grad}\,\phi+Sr+\mathbf{h}$ in two dimensions and $\mathrm{grad}\,\phi+\mathbf{z}$ in two and three dimensions. In all of them every interface jump of the field is carried by the potential term, $\mathrm{Div}\,A$ or $\mathrm{grad}\,\phi$, while the remaining part has no interface jump (it is an $H^1$ field in the regular-decomposition classes); the classes with $\mathbf{z}$ are the componentwise approach enriched by this term. Known or learned interface geometry enters the potential through factors with trainable amplitudes, and the remaining part if the divergence jumps. The classes lead to the FOSLS-deRhaNN method, first-order system least squares with de Rham neural networks, whose loss is the least-squares functional posed in the natural spaces of the weak formulation; for elliptic equations this includes $H^{-1}$ right-hand sides and $H^{1/2}$ Dirichlet data. Elliptic equations with discontinuous coefficients and curl-curl problems are treated as instances, with the functional equivalent to the error; linear transport with discontinuous solutions and conservation laws with shocks use the same flux classes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.08016 — 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 2026-10-07T11:19:24.927Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).