ODEFormer: Symbolic Regression of Dynamical Systems With Transformers

MCML Authors

Sören Becker

* Former Member

→ Group Niki Kilbertus
 Ethics in Systems Design and Machine Learning

Niki Kilbertus

Prof. Dr.

Core PI

Ethics in Systems Design and Machine Learning

Abstract

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.

inproceedings ABS+24

---

ICLR 2024

12th International Conference on Learning Representations. Vienna, Austria, May 07-11, 2024.

---

Authors

S. d'Ascoli • S. Becker • P. Schwaller • A. Mathis • N. Kilbertus

---

Links

URL GitHub

---

Research Area

 A3 | Computational Models