Metraipolis › archive › dc_e95f88778354

Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates — arXiv:2610.05375

Source
arXiv
Original
https://arxiv.org/abs/2610.05375
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:08.624Z
SHA-256 of the archived text
33c67e414c85eb315bb2d01f067bc5a48b150200f5d1699858e193e38972c2d8
Stable URL of this page
https://metraipolis.com/documento/dc_e95f88778354

How to cite

Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates — arXiv:2610.05375 — arXiv, https://arxiv.org/abs/2610.05375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e95f88778354 (Metraipolis archive dc_e95f88778354, sha256 33c67e414c85eb315bb2d01f067bc5a48b150200f5d1699858e193e38972c2d8)
BibTeX
@misc{dce95f88778354,
  title = {Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates — arXiv:2610.05375},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e95f88778354; sha256 33c67e414c85eb315bb2d01f067bc5a48b150200f5d1699858e193e38972c2d8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing physical fields from training samples that are always incomplete requires learning spatial structure from fragmented this http URL context--query work establishes how held-out observations provide valid training targets, but this does not make the complete-field distribution identifiable when every training field is this http URL finite data, weak evidence of sharp transitions and localized variations can further favor averaged predictions that attenuate local detail.A structural prior is therefore needed to favor plausible completions; local spatial relationships offer one grounded in the this http URL propose a locally constructed, globally revisable estimator that explicitly learns local field estimates and subsequently corrects them using full-domain observations.A shared coordinate-conditioned predictor learns from incomplete patches, allowing relatively well-observed neighborhoods to provide direct supervision of local this http URL overlapping predictions are reconciled into an observation-conditioned consensus field.A full-domain estimator retains the original observations and learns a residual correction around this frozen field estimate, allowing locally constructed structure to be revised by broader this http URL local estimate serves as both an explicit input, accompanied by its discrepancies with the observations, and a prediction starting point that the global model can this http URL three real-world ocean datasets with authentic observation gaps, our estimator achieves the lowest MSE and highest PSNR on withheld source-supported values, reducing MSE by 28.9\%--34.5\% against the strongest external baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05375 — 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 2026-10-06T05:24:05.580Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).