Spotlight Poster
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
Stéphane d'Ascoli · Sören Becker · Philippe Schwaller · Alexander Mathis · Niki Kilbertus
Halle B
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 dataset publicly.
Chat is not available.