Metraipolis › archive › dc_87d37fdacf44

Ermakov--Based embeddings as a parameter-free layer for physics-informed neural networks — arXiv:2611.03964

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03964
License (as archived)
CC0-1.0
Archived
2026-11-04T21:50:53.939Z
SHA-256 of the archived text
b7671cd7c3b9c2cee81d95c597e11001084e121e71b78cbe6e1951f01b037103
Stable URL of this page
https://metraipolis.com/documento/dc_87d37fdacf44

How to cite

Ermakov--Based embeddings as a parameter-free layer for physics-informed neural networks — arXiv:2611.03964 — arXiv (en), https://arxiv.org/abs/2611.03964 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87d37fdacf44 (Metraipolis archive dc_87d37fdacf44, sha256 b7671cd7c3b9c2cee81d95c597e11001084e121e71b78cbe6e1951f01b037103)
BibTeX
@misc{dc87d37fdacf44,
  title = {Ermakov--Based embeddings as a parameter-free layer for physics-informed neural networks — arXiv:2611.03964},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03964},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87d37fdacf44; sha256 b7671cd7c3b9c2cee81d95c597e11001084e121e71b78cbe6e1951f01b037103},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03964. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evolution equations with time-dependent coefficients force a neural solver to spend capacity on a scale that the equation already determines. We show that a single classical object, the Ermakov-Pinney scale function $\rho$, can be written into the input layer of a physics-informed neural network as a parameter-free embedding. One construction covers three problem families through the two signs of the Pinney constant $c$: linear diffusion ($c=-1$, $\omega\equiv0$), diffusion in a time-dependent confining trap ($c=-1$, $\omega\neq0$), and the quantum oscillator with time-dependent frequency ($c=+1$). An exact moment identity gives $\rho$ in closed form from the initial data alone, so no auxiliary network or knowledge of the solution is needed. Our central finding is comparative: each family requires a different component of the construction and has a different honest control. In family I, the diffusive-time reparametrisation alone reproduces most of the gain, so that family is a poor test of the idea and shows why an ablation is mandatory. In family II no time reparametrisation exists, the control degrades accuracy, and the amplitude prefactor becomes essential (40.8x). In family III the adiabatic approximation also fails, and the quadratic phase factor is what matters (5.7x). The method does not help when the reduced solution does not converge to a fixed point: its extrapolation advantage then disappears. The reduction itself is the classical scaling-variable change of the self-similar-asymptotics literature; what is new is the moment identity that makes it architectural for time-dependent coefficients, and the comparative anatomy above.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03964 — 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 2026-11-04T21:38:49.684Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).