Home | Publications | ABS+24

ODEFormer: Symbolic Regression of Dynamical Systems With Transformers

MCML Authors

Link to Profile Niki Kilbertus PI Matchmaking

Niki Kilbertus

Prof. Dr.

Core PI

AI for Scientific Modeling

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.
Conference logo
A* Conference

Authors

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

Links

URL GitHub

Research Area

 A3 | Computational Models

BibTeXKey: ABS+24

#p-kilbertus
Back to Top