Metraipolis › archive › dc_3d4eaa3daa73

CasEm: A Cascade Architecture for Long-Horizon Neural Emulation — arXiv:2609.34246

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34246
License (as archived): CC0-1.0
Archived: 2026-10-07T22:38:06.537Z
SHA-256 of the archived text: a6080c25075f450f1a758027e6646819d62a33179769a21402fb52075aba7be0
Stable URL of this page: https://metraipolis.com/documento/dc_3d4eaa3daa73

How to cite

CasEm: A Cascade Architecture for Long-Horizon Neural Emulation — arXiv:2609.34246 — arXiv (en), https://arxiv.org/abs/2609.34246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d4eaa3daa73 (Metraipolis archive dc_3d4eaa3daa73, sha256 a6080c25075f450f1a758027e6646819d62a33179769a21402fb52075aba7be0)

BibTeX

@misc{dc3d4eaa3daa73,
  title = {CasEm: A Cascade Architecture for Long-Horizon Neural Emulation — arXiv:2609.34246},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34246},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d4eaa3daa73; sha256 a6080c25075f450f1a758027e6646819d62a33179769a21402fb52075aba7be0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive neural emulators can drift or diverge over long rollouts despite accurate short-term predictions. We introduce Cascaded Emulation (CasEm), a one-way rollout architecture that augments an existing full-state backbone with an independently evolving model of physically specified aggregates. Its forecasts guide corrections to full-state predictions, without feedback from the backbone to the aggregate model. Effective guidance requires aggregates that cover substantial backbone error, remain accurately predictable, and support useful full-state corrections. We derive a finite-horizon error bound that clarifies these three factors and use empirical diagnostics to guide subsystem selection. Across four ODE/PDE benchmarks, CasEm reduces long-horizon rollout errors across diverse backbones and suppresses the trend toward error divergence in both diffusion tasks using Fourier neural operator backbones. In global climate emulation, CasEm with a regional total-water subsystem reduces 10-year full-state time-mean error by 66.6% and 46.3% for frozen ACE and Spherical DYffusion backbones, respectively, while adding less than 3% to inference time.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.34246 — 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 2026-10-07T22:14:28.141Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).