Learning Reversible Symplectic Dynamics

Riccardo Valperga, Kevin Webster, Dmitry Turaev, Victoria Klein, Jeroen Lamb
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:906-916, 2022.

Abstract

Time-reversal symmetry arises naturally as a structural property in many dynamical systems of interest. While the importance of hard-wiring symmetry is increasingly recognized in machine learning, to date this has eluded time-reversibility. In this paper, we propose a new neural network architecture for learning time-reversible dynamical systems from data. We focus in particular on an adaptation to symplectic systems, because of their importance in physics-informed learning.

Cite this Paper


BibTeX
@InProceedings{pmlr-v168-valperga22a, title = {Learning Reversible Symplectic Dynamics}, author = {Valperga, Riccardo and Webster, Kevin and Turaev, Dmitry and Klein, Victoria and Lamb, Jeroen}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {906--916}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/valperga22a/valperga22a.pdf}, url = {https://proceedings.mlr.press/v168/valperga22a.html}, abstract = {Time-reversal symmetry arises naturally as a structural property in many dynamical systems of interest. While the importance of hard-wiring symmetry is increasingly recognized in machine learning, to date this has eluded time-reversibility. In this paper, we propose a new neural network architecture for learning time-reversible dynamical systems from data. We focus in particular on an adaptation to symplectic systems, because of their importance in physics-informed learning.} }
Endnote
%0 Conference Paper %T Learning Reversible Symplectic Dynamics %A Riccardo Valperga %A Kevin Webster %A Dmitry Turaev %A Victoria Klein %A Jeroen Lamb %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-valperga22a %I PMLR %P 906--916 %U https://proceedings.mlr.press/v168/valperga22a.html %V 168 %X Time-reversal symmetry arises naturally as a structural property in many dynamical systems of interest. While the importance of hard-wiring symmetry is increasingly recognized in machine learning, to date this has eluded time-reversibility. In this paper, we propose a new neural network architecture for learning time-reversible dynamical systems from data. We focus in particular on an adaptation to symplectic systems, because of their importance in physics-informed learning.
APA
Valperga, R., Webster, K., Turaev, D., Klein, V. & Lamb, J.. (2022). Learning Reversible Symplectic Dynamics. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:906-916 Available from https://proceedings.mlr.press/v168/valperga22a.html.

Related Material