ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
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. We release our code, model and benchmark at https://github.com/sdascoli/odeformer.
Cite
Text
d'Ascoli et al. "ODEFormer: Symbolic Regression of Dynamical Systems with Transformers." International Conference on Learning Representations, 2024.Markdown
[d'Ascoli et al. "ODEFormer: Symbolic Regression of Dynamical Systems with Transformers." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/dascoli2024iclr-odeformer/)BibTeX
@inproceedings{dascoli2024iclr-odeformer,
title = {{ODEFormer: Symbolic Regression of Dynamical Systems with Transformers}},
author = {d'Ascoli, Stéphane and Becker, Sören and Schwaller, Philippe and Mathis, Alexander and Kilbertus, Niki},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/dascoli2024iclr-odeformer/}
}