Metraipolis › archive › dc_bece86311d52
A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training — arXiv:2609.13171
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13171
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:10:12.716Z
- SHA-256 of the archived text
b66f8433686a6bd1cada901254ba240691d67e0106935ddb564ebdbfe731731a- Stable URL of this page
https://metraipolis.com/documento/dc_bece86311d52
How to cite
A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training — arXiv:2609.13171 — arXiv (en), https://arxiv.org/abs/2609.13171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bece86311d52 (Metraipolis archive dc_bece86311d52, sha256 b66f8433686a6bd1cada901254ba240691d67e0106935ddb564ebdbfe731731a)
BibTeX
@misc{dcbece86311d52,
title = {A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training — arXiv:2609.13171},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13171},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bece86311d52; sha256 b66f8433686a6bd1cada901254ba240691d67e0106935ddb564ebdbfe731731a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physics-informed neural networks (PINNs) use automatic differentiation to impose differential-equation residuals, but good agreement in function values does not necessarily imply accurate derivatives. This paper formulates derivative fidelity as a failure mode of PINNs and tests it with one-dimensional benchmarks. Multilayer perceptrons are trained only on function values for sin(x) and exp(x), while second derivatives obtained by automatic differentiation are evaluated separately. The hypothesis is strengthened by additional tests over training-point density, activation functions, endpoint-dense evaluation, and both L2 and maximum-error diagnostics. The results show that visually accurate function approximation can coexist with substantially larger second-derivative errors, especially near high-curvature boundary regions. The experiment provides a diagnostic protocol for distinguishing value accuracy from physics-residual reliability. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.13171 — 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 2026-10-15T23:54:14.590Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).