Metraipolis › archive › dc_f6c07970edfe

Learning in the Transverse Subspace: A Minimal Representation for Divergence-Free Operator Learning — arXiv:2609.35884

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35884
License (as archived)
CC0-1.0
Archived
2026-10-07T17:28:33.857Z
SHA-256 of the archived text
b490490b8a17598f08bf99789148c0dc21d3fc33fe5f5e283192478a6f715361
Stable URL of this page
https://metraipolis.com/documento/dc_f6c07970edfe

How to cite

Learning in the Transverse Subspace: A Minimal Representation for Divergence-Free Operator Learning — arXiv:2609.35884 — arXiv (en), https://arxiv.org/abs/2609.35884 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6c07970edfe (Metraipolis archive dc_f6c07970edfe, sha256 b490490b8a17598f08bf99789148c0dc21d3fc33fe5f5e283192478a6f715361)
BibTeX
@misc{dcf6c07970edfe,
  title = {Learning in the Transverse Subspace: A Minimal Representation for Divergence-Free Operator Learning — arXiv:2609.35884},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35884},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6c07970edfe; sha256 b490490b8a17598f08bf99789148c0dc21d3fc33fe5f5e283192478a6f715361},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35884. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Divergence-free vector fields are fundamental state variables in incompressible flows and many PDE systems. Redundant parameterizations, including Neural Conservation Law (NCL) potentials, map multiple auxiliary representations to the same physical field. Our experiments show that this redundancy can reduce static representation-fitting error by enlarging the set of equivalent solutions, but the resulting many-to-one mapping does not provide a unique state for operator learning. We introduce a minimal representation that encodes a real \(D\)-component divergence-free vector field on a \(D\)-dimensional domain as a real \((D-1)\)-component field on the same domain. Exploiting the transverse structure imposed by incompressibility in Fourier space, we use a Householder orthogonal transformation to construct the reduced coordinates directly. For periodic and closed impermeable fields, the transform is invertible, isometric, and angle-preserving. For open nonperiodic flows, Fourier extension constructs a compatible periodic field, and a minimum-energy rule selects a unique reduced representation. Neural operators then learn temporal evolution entirely in this reduced space. At inference, the predicted \((D-1)\)-component field is decoded directly into a physical divergence-free \(D\)-component field, without predicting an ambient field or applying post-hoc projection. Experiments on static fitting and temporal prediction reveal a task-dependent trade-off: redundancy facilitates static optimization, whereas unique invertible coordinates provide a well-defined state for temporal dynamics. By removing unconstrained longitudinal or null directions from the learned state space, the proposed formulation achieves lower prediction error and greater robustness while preserving divergence freedom by construction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Fluid Dynamics (physics.flu-dyn).
Pagina del lavoro: https://arxiv.org/abs/2609.35884 — 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 2026-10-07T16:59:48.074Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).