PuSH - Publikationsserver des Helmholtz Zentrums München

d'Ascoli,  S.* ; Becker, S. ; Mathis, A.* ; Schwaller, P.* ; Kilbertus, N.

ODEFormer: Symbolic regression of dynamical systems with transformers.

In: (12th International Conference on Learning Representations, ICLR 2024, 07-11 May 2024, Hybrid, Vienna). 2024.
Verlagsversion
We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory. We perform extensive evaluations on two datasets: (i) the existing 'Strogatz' dataset featuring two-dimensional systems; (ii) ODEBench, a collection of one- to four-dimensional systems that we carefully curated from the literature to provide a more holistic benchmark. ODEFormer consistently outperforms existing methods while displaying substantially improved robustness to noisy and irregularly sampled observations, as well as faster inference. We release our code, model and benchmark at https://github.com/sdascoli/odeformer. © 2024 12th International Conference on Learning Representations, ICLR 2024.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Konferenztitel 12th International Conference on Learning Representations, ICLR 2024
Konferzenzdatum 07-11 May 2024
Konferenzort Hybrid, Vienna
Nichtpatentliteratur Publikationen
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute of Computational Biology (ICB)