Metraipolis › archive › dc_70386ee2b15c
F$^3$NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning — arXiv:2610.10998
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10998
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:21:10.671Z
- SHA-256 of the archived text
2fa04fd966728f5448f31116c12ac8ed32bfc6998f26cdb7eb086b75f9500984- Stable URL of this page
https://metraipolis.com/documento/dc_70386ee2b15c
How to cite
F$^3$NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning — arXiv:2610.10998 — arXiv (en), https://arxiv.org/abs/2610.10998 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70386ee2b15c (Metraipolis archive dc_70386ee2b15c, sha256 2fa04fd966728f5448f31116c12ac8ed32bfc6998f26cdb7eb086b75f9500984)
BibTeX
@misc{dc70386ee2b15c,
title = {F$^3$NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning — arXiv:2610.10998},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10998},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70386ee2b15c; sha256 2fa04fd966728f5448f31116c12ac8ed32bfc6998f26cdb7eb086b75f9500984},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10998. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural operators enable fast PDE forecasting, but repeated predictions accumulate errors and fine-scale structures remain difficult to resolve. We introduce a frequency-decomposed finite-time flow-map neural operator (F$^3$NO) that leverages updated low-frequency features to guide nonlinear refinement of high-frequency information. Within each layer, this cross-scale conditioning connects global spectral processing with local detail refinement. The model directly predicts states at specified future times and adjusts the contributions of the two branches according to the prediction interval. For longer trajectories, it combines parallel predictions within short temporal segments with recursive propagation between segments. Experiments on five PDE benchmarks demonstrate improved forecasting accuracy over autoregressive and direct-prediction baselines. Ablations show that frequency-decomposed refinement can improve accuracy with fewer parameters, while the benefits of segmentation depend on spatial resolution and dynamical regime. 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/2610.10998 — 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 2026-10-09T05:50:31.093Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).