Metraipolis › archive › dc_2f877556da14
The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning — arXiv:2609.33078
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33078
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:37:09.076Z
- SHA-256 of the archived text
41a3e40a549e514bfb7ac2a3ed5f84c07ead01e1b7522fb49a58ffbb7a4258a5- Stable URL of this page
https://metraipolis.com/documento/dc_2f877556da14
How to cite
The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning — arXiv:2609.33078 — arXiv (en), https://arxiv.org/abs/2609.33078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f877556da14 (Metraipolis archive dc_2f877556da14, sha256 41a3e40a549e514bfb7ac2a3ed5f84c07ead01e1b7522fb49a58ffbb7a4258a5)
BibTeX
@misc{dc2f877556da14,
title = {The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning — arXiv:2609.33078},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33078},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f877556da14; sha256 41a3e40a549e514bfb7ac2a3ed5f84c07ead01e1b7522fb49a58ffbb7a4258a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automatic differentiation (AD) lets neural networks compute derivatives of governing equations to machine precision, and this precision has made it the computational backbone of physics-informed machine learning. Yet exactness in the mathematical sense is not the same as fidelity to the physics. Here I argue that a derivative can be numerically perfect and still be the wrong derivative for the problem at hand, because AD, by construction, has no notion of the physical structure a solution must obey. Convection and its associated directionality, diffusion, and dispersion are only the most visible instances of a much longer list that spans all branches of computational science and engineering, including conservation, thermodynamic consistency, symmetry, symplectic structure, positivity, monotonicity, and boundedness. Recognizing this broader gap reframes how the field should build the next generation of PDE-driven neural surrogates. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33078 — 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 2026-10-07T22:14:27.858Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).