Metraipolis › archive › dc_cb822f306e1f

Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies — arXiv:2608.10738

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10738
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:26.213Z
SHA-256 of the archived text
d2b13e44b8999b35aa5aad26298d35a1ac70c7ffa8ef7b01d119f4d375ff1aef
Stable URL of this page
https://metraipolis.com/documento/dc_cb822f306e1f

How to cite

Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies — arXiv:2608.10738 — arXiv (en), https://arxiv.org/abs/2608.10738 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb822f306e1f (Metraipolis archive dc_cb822f306e1f, sha256 d2b13e44b8999b35aa5aad26298d35a1ac70c7ffa8ef7b01d119f4d375ff1aef)
BibTeX
@misc{dccb822f306e1f,
  title = {Long-Time Trajectory Approximation via SA-NODEs: Model Predictive and Floquet Strategies — arXiv:2608.10738},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10738},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb822f306e1f; sha256 d2b13e44b8999b35aa5aad26298d35a1ac70c7ffa8ef7b01d119f4d375ff1aef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10738. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a single network trained on the whole horizon, the available error bound deteriorates double exponentially in the horizon length. We develop two training strategies that avoid this barrier, each built on a reset of the state. The model predictive strategy partitions the horizon adaptively and restarts every window from observed data: when training meets a prescribed tolerance on every window, the composite model meets it uniformly in time, with a parameter budget linear in the horizon for targets with a bounded, uniformly regular reachable tube. The Floquet strategy addresses autonomous targets with a stable limit cycle and uses no data at deployment: a certified contraction of the learned return map confines the error to linear growth in the number of elapsed periods. For the time-periodic architecture we deploy, the scalar certificate degenerates; we prove instead a uniform-in-time orbital guarantee whose hypotheses are measured on the trained model, and an obstruction showing that, for an exactly periodic learned field, small one-period error and a contracting stroboscopic map cannot hold at once. Numerical experiments on four benchmarks confirm the predicted error laws and measure the hypotheses of every guarantee.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.10738 — 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 2026-10-19T06:11:45.092Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).