EUVIMEDEUVIMED entdecken
Crossref

CODE: A GLOBAL APPROACH TO ODE DYNAMICS LEARNING

Nils Wildt, Daniel M. Tartakovsky, Sergey Oladyshkin, Wolfgang Nowak

Journal of Machine Learning for Modeling and Computing · 2026 · 7 (2) · 73-105

DOI: 10.1615/jmachlearnmodelcomput.2026062518 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Machine Learning for Modeling and Computing, 2026. Verfasst von Nils Wildt und 3 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ordinary differential equations (ODEs) are a conventional way to describe the observed dynamics of physical systems. Scientists typically hypothesize about dynamical behavior, propose a mathematical model, and compare its predictions to data. However, modern computing and algorithmic advances now enable purely data-driven learning of governing dynamics directly from observations. In data-driven settings, one learns the ODE's right-hand side (RHS). Dense measurements are often assumed, yet high temporal resolution is typically both cumbersome and expensive. Consequently, one usually has only sparsely sampled data. In this work we introduce ChaosODE (CODE), a polynomial chaos ODE expansion in which we use an arbitrary polynomial chaos expansion (aPCE) for the ODE's RHS, resulting in a global orthonormal polynomial representation of dynamics. We evaluate the performance of CODE in several experiments on the Lotka-Volterra system, across varying noise levels, initial conditions, and predictions far into the future, even on previously unseen initial conditions. CODE exhibits remarkable extrapolation capabilities even when evaluated under novel initial conditions and shows advantages compared to well-examined methods using neural networks (NeuralODE) or kernel approximators (KernelODE) as the RHS representer. We observe that the high flexibility of NeuralODE and KernelODE degrades extrapolation capabilities under scarce data and measurement noise. Finally, we provide practical guidelines for robust optimization of dynamics-learning problems and illustrate them in the accompanying code.

Zitieren

APA

Wildt, N., Tartakovsky, D. M., Oladyshkin, S., & Nowak, W. (2026). CODE: A GLOBAL APPROACH TO ODE DYNAMICS LEARNING. Journal of Machine Learning for Modeling and Computing, 7(2), 73-105. https://doi.org/10.1615/jmachlearnmodelcomput.2026062518

Vancouver

Wildt N, Tartakovsky DM, Oladyshkin S, Nowak W. CODE: A GLOBAL APPROACH TO ODE DYNAMICS LEARNING. Journal of Machine Learning for Modeling and Computing. 2026;7(2):73-105. doi:10.1615/jmachlearnmodelcomput.2026062518

BibTeX
@article{Wildt2026,
  author = {Wildt, Nils and Tartakovsky, Daniel M. and Oladyshkin, Sergey and Nowak, Wolfgang},
  title = {CODE: A GLOBAL APPROACH TO ODE DYNAMICS LEARNING},
  journal = {Journal of Machine Learning for Modeling and Computing},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {73--105},
  doi = {10.1615/jmachlearnmodelcomput.2026062518}
}
Kostenlos starten →