Metraipolis › archive › dc_e764d84cfdd3
Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations — arXiv:2608.05777
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05777
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:06:04.193Z
- SHA-256 of the archived text
51aa3aafb2a379a459c69e58316eabe0575b4301f85e2efba8b94deca88f6b1a- Stable URL of this page
https://metraipolis.com/documento/dc_e764d84cfdd3
How to cite
Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations — arXiv:2608.05777 — arXiv (en), https://arxiv.org/abs/2608.05777 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e764d84cfdd3 (Metraipolis archive dc_e764d84cfdd3, sha256 51aa3aafb2a379a459c69e58316eabe0575b4301f85e2efba8b94deca88f6b1a)
BibTeX
@misc{dce764d84cfdd3,
title = {Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations — arXiv:2608.05777},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05777},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e764d84cfdd3; sha256 51aa3aafb2a379a459c69e58316eabe0575b4301f85e2efba8b94deca88f6b1a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05777. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural ordinary differential equations (NODEs) and universal differential equations (UDEs) provide flexible and popular frameworks for learning interpretable dynamical systems from noisy time-series data. However, training these models remains challenging, and versatile methods that robustly handle sparse and noisy data as well as partially observed models are lacking. To address this, we introduce curriculum multiple shooting (CMS), a general-purpose training strategy for fitting ordinary differential equation (ODE) models to time-series data by integrating curriculum learning with multiple shooting. Across twelve benchmarks spanning simulated and real data, and covering NODEs, UDEs, and mechanistic ODEs, CMS accelerates and stabilises training convergence, outperforms state-of-the-art training strategies, and ranks among the best methods in generalisation. Finally, we discuss possible explanations for the strong performance of CMS in light of contemporary theories of what makes training on time-series challenging. Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-08-07 in q-bio.QM). Categorie arXiv: Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2608.05777 — 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 2026-10-31T10:56:00.840Z dalla pagina https://arxiv.org/catchup/q-bio.QM/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).