Predicting Ordinary Differential Equations with Transformers
Abstract
We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observations of a single solution trajectory. We demonstrate in extensive empirical evaluations that our model performs better or on par with existing methods in terms of accurate recovery across various settings. Moreover, our method is efficiently scalable: after one-time pretraining on a large set of ODEs, we can infer the governing law of a new observed solution in a few forward passes of the model.
Cite
Text
Becker et al. "Predicting Ordinary Differential Equations with Transformers." International Conference on Machine Learning, 2023.Markdown
[Becker et al. "Predicting Ordinary Differential Equations with Transformers." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/becker2023icml-predicting/)BibTeX
@inproceedings{becker2023icml-predicting,
title = {{Predicting Ordinary Differential Equations with Transformers}},
author = {Becker, Sören and Klein, Michal and Neitz, Alexander and Parascandolo, Giambattista and Kilbertus, Niki},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {1978-2002},
volume = {202},
url = {https://mlanthology.org/icml/2023/becker2023icml-predicting/}
}