Metraipolis › archive › dc_2f9c8ed7e7eb

Symbolic Neural ODEs: Learning interpretable models from time-series data — arXiv:2608.22112

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22112
License (as archived)
CC0-1.0
Archived
2026-10-18T10:09:22.354Z
SHA-256 of the archived text
dc2e89b6d70eb25ed782a6a4e1f7016740aeccb8cb02d569aa4f3028720f71be
Stable URL of this page
https://metraipolis.com/documento/dc_2f9c8ed7e7eb

How to cite

Symbolic Neural ODEs: Learning interpretable models from time-series data — arXiv:2608.22112 — arXiv (en), https://arxiv.org/abs/2608.22112 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f9c8ed7e7eb (Metraipolis archive dc_2f9c8ed7e7eb, sha256 dc2e89b6d70eb25ed782a6a4e1f7016740aeccb8cb02d569aa4f3028720f71be)
BibTeX
@misc{dc2f9c8ed7e7eb,
  title = {Symbolic Neural ODEs: Learning interpretable models from time-series data — arXiv:2608.22112},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22112},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f9c8ed7e7eb; sha256 dc2e89b6d70eb25ed782a6a4e1f7016740aeccb8cb02d569aa4f3028720f71be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22112. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a machine learning framework for identifying sparse, interpretable models of dynamical systems directly from time-series data. Our approach parameterizes the underlying vector field using a neural architecture and trains it by minimizing a multi-step prediction loss over a finite horizon. To ensure numerical tractability, we optimize a mean absolute error objective averaged across prediction steps, and progressively increase the horizon during training. A key feature of this formulation is that it enforces consistency under repeated composition of the learned dynamics. As a result, the identified models exhibit significantly improved stability compared with approaches based on one-step regression of the vector field. When combined with sparsity-promoting regularization, this leads to parsimonious models that generalize beyond the training data. We demonstrate accurate recovery of systems exhibiting a wide range of behaviors, including stable and unstable fixed points, periodic orbits, and chaotic attractors. For chaotic systems, while long-term trajectory prediction is inherently limited by sensitivity to initial conditions, we show that multi-step training yields models with accurate short-term dynamics and strong agreement in long-time statistical properties, including mean, variance, and Lyapunov exponents. Moreover, we establish theoretical bounds linking trajectory error to statistical accuracy, providing a step toward a principled explanation for this behavior.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in eess.SY).
Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY); Dynamical Systems (math.DS); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.22112 — 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 2026-10-18T10:08:09.911Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).