Metraipolis › archive › dc_6c2f27aff045

MiNO: Cotangent-bundle propagator learning for PDEs — arXiv:2608.15187

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15187
License (as archived)
CC0-1.0
Archived
2026-10-18T19:40:07.063Z
SHA-256 of the archived text
848f1513f3dd3ee62be89856ef9f1bfb0580d4e40eac873c16e35bcd1361c195
Stable URL of this page
https://metraipolis.com/documento/dc_6c2f27aff045

How to cite

MiNO: Cotangent-bundle propagator learning for PDEs — arXiv:2608.15187 — arXiv (en), https://arxiv.org/abs/2608.15187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c2f27aff045 (Metraipolis archive dc_6c2f27aff045, sha256 848f1513f3dd3ee62be89856ef9f1bfb0580d4e40eac873c16e35bcd1361c195)
BibTeX
@misc{dc6c2f27aff045,
  title = {MiNO: Cotangent-bundle propagator learning for PDEs — arXiv:2608.15187},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15187},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c2f27aff045; sha256 848f1513f3dd3ee62be89856ef9f1bfb0580d4e40eac873c16e35bcd1361c195},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific machine learning for partial differential equations commonly targets solution fields, as in physics-informed neural networks, or solution maps, as in neural operators. We study a third target: the propagator itself, a phase and amplitude in phase space. The motivation is a gap in regularity. A transported discontinuity is nonsmooth in space and time, yet the rule that moves it can be a polynomial phase carrying unit amplitude, so the object that generates an evolution can be far smoother than the field it generates. The microlocal neural operator (MiNO) learns that object, using the eikonal equation for the phase and the transport equation for the amplitude, and recovers the solution by an oscillatory integral. Sharp fronts and caustics then belong to propagation geometry rather than to a field fitted pointwise. Small residuals certify more than the reconstructed field. They place the learned canonical relation, the geometry that carries singularities, close to the exact one, and they separate trainable error from the frequency-truncation tail. On a matched-budget discontinuous-advection benchmark, MiNO stops improving within 10,000 steps at the accuracy limit of its finite reconstruction window, a limit predicted in closed form, whereas a physics-informed neural network with neural-tangent-kernel loss balancing stays near its initial error. On smooth advection, the mean error is $3.84\times10^{-3}$ for MiNO and $3.12\times10^{-2}$ for a supervised Fourier neural operator. Single-branch MiNO is the smallest model compared, and one trained generator serves five unseen initial conditions without retraining.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Engineering, Finance, and Science (cs.CE); Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.15187 — 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 2026-10-18T19:02:44.078Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).