Metraipolis › archive › dc_7940f9f178cf

Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics — arXiv:2610.10626

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10626
License (as archived)
CC0-1.0
Archived
2026-10-09T06:20:51.651Z
SHA-256 of the archived text
3b179582f8e8cc793b20052369aef7015ae4e82c0dc1eb8e840aec41dc56fd89
Stable URL of this page
https://metraipolis.com/documento/dc_7940f9f178cf

How to cite

Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics — arXiv:2610.10626 — arXiv (en), https://arxiv.org/abs/2610.10626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7940f9f178cf (Metraipolis archive dc_7940f9f178cf, sha256 3b179582f8e8cc793b20052369aef7015ae4e82c0dc1eb8e840aec41dc56fd89)
BibTeX
@misc{dc7940f9f178cf,
  title = {Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics — arXiv:2610.10626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7940f9f178cf; sha256 3b179582f8e8cc793b20052369aef7015ae4e82c0dc1eb8e840aec41dc56fd89},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural surrogates for vector-valued partial differential equations can fit training data yet change their predictions when the same physical state is expressed in a rotated coordinate frame. We study this failure on three-dimensional Navier--Stokes dynamics observed at irregularly placed points. We introduce the Invariant-Conditioned Isotropic Kernel Neural Operator (IKNO), a compact graph model that builds local interactions from scalar quantities unchanged by rotation and vector directions that rotate with the data. Consequently, rotating the positions and velocities rotates the predicted velocity change in exactly the same way. On a held-out test set fixed after model design, training unconstrained graph models on randomly rotated examples reduces but does not eliminate their coordinate dependence. In contrast, IKNO is consistent to numerical precision, matches the forecasting accuracy of a general rotation-aware Tensor Field Network with $5.6$ times fewer parameters, and outperforms a parameter-matched graph simulator. These results show that a compact, PDE-specialized model can remove coordinate dependence without sacrificing forecasting accuracy.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Engineering, Finance, and Science (cs.CE); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.10626 — 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 2026-10-09T05:50:30.887Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).