Metraipolis › archive › dc_4ad7064099fb

Learning piecewise-smooth dynamical systems — arXiv:2608.19785

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19785
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:43.801Z
SHA-256 of the archived text
3611b8a977de0693794c47e7e8459ae96431571e81fd2d433334f1ba78bd578a
Stable URL of this page
https://metraipolis.com/documento/dc_4ad7064099fb

How to cite

Learning piecewise-smooth dynamical systems — arXiv:2608.19785 — arXiv (en), https://arxiv.org/abs/2608.19785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ad7064099fb (Metraipolis archive dc_4ad7064099fb, sha256 3611b8a977de0693794c47e7e8459ae96431571e81fd2d433334f1ba78bd578a)
BibTeX
@misc{dc4ad7064099fb,
  title = {Learning piecewise-smooth dynamical systems — arXiv:2608.19785},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19785},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ad7064099fb; sha256 3611b8a977de0693794c47e7e8459ae96431571e81fd2d433334f1ba78bd578a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discovering dynamical systems from trajectory data is a central problem in applied mathematics and engineering. Whilst recent advances in machine learning have led to strong progress in data-driven system identification, much less attention has been given to systems with discontinuous dynamics. These systems are nevertheless highly relevant in applications, including climate dynamics and mechanical systems with friction. In this work, we consider the problem of identifying piecewise-smooth dynamical systems directly from trajectory data. Compared with the smooth setting, this requires recovering the governing equations and detecting the switching hyperplanes that separate different dynamical regimes and characterising their behaviour, such as sliding motion. We present a modular framework for discovering such systems by first estimating switching hyperplanes from data and then learning smooth dynamics within each region using geometry-constrained neural networks. The geometry-learning phase is studied from a statistical perspective, analysing the identifiability of the discontinuities and the robustness of the procedure. We also introduce a novel neural network architecture with a prescribed discontinuity set, and provide a theoretical analysis of its approximation properties. The approach is tested on low-dimensional benchmark problems, including dry-friction oscillators and the PP04 climate model for the ice ages.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Dynamical Systems (math.DS) ; Machine Learning (cs.LG); Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.19785 — 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 2026-10-18T11:47:43.376Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).