Learning Dynamical Systems with Side Information
Abstract
We present a mathematical formalism and a computational framework for the problem of learning a dynamical system from noisy observations of a few trajectories and subject to side information (e.g., physical laws or contextual knowledge). We identify six classes of side information which can be imposed by semidefinite programming and that arise naturally in many applications. We demonstrate their value on two examples from epidemiology and physics. Some density results on polynomial dynamical systems that either exactly or approximately satisfy side information are also presented.
Cite
Text
Ahmadi and El Khadir. "Learning Dynamical Systems with Side Information." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.Markdown
[Ahmadi and El Khadir. "Learning Dynamical Systems with Side Information." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.](https://mlanthology.org/l4dc/2020/ahmadi2020l4dc-learning/)BibTeX
@inproceedings{ahmadi2020l4dc-learning,
title = {{Learning Dynamical Systems with Side Information}},
author = {Ahmadi, Amir Ali and El Khadir, Bachir},
booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control},
year = {2020},
pages = {718-727},
volume = {120},
url = {https://mlanthology.org/l4dc/2020/ahmadi2020l4dc-learning/}
}