Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution

Rui Wang, Elyssa Hofgard, Han Gao, Robin Walters, Tess Smidt
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50599-50621, 2024.

Abstract

Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics and cosmic structures. Thus, identifying sources of asymmetry is an important tool for understanding physical systems. In this paper, we focus on learning asymmetries of data using relaxed group convolutions. We provide both theoretical and empirical evidence that this flexible convolution technique allows the model to maintain the highest level of equivariance that is consistent with data and discover the subtle symmetry-breaking factors in various physical systems. We employ various relaxed group convolution architectures to uncover various symmetry-breaking factors that are interpretable and physically meaningful in different physical systems, including the phase transition of crystal structure, the isotropy and homogeneity breaking in turbulent flow, and the time-reversal symmetry breaking in pendulum systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wang24y, title = {Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution}, author = {Wang, Rui and Hofgard, Elyssa and Gao, Han and Walters, Robin and Smidt, Tess}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {50599--50621}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/wang24y/wang24y.pdf}, url = {https://proceedings.mlr.press/v235/wang24y.html}, abstract = {Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics and cosmic structures. Thus, identifying sources of asymmetry is an important tool for understanding physical systems. In this paper, we focus on learning asymmetries of data using relaxed group convolutions. We provide both theoretical and empirical evidence that this flexible convolution technique allows the model to maintain the highest level of equivariance that is consistent with data and discover the subtle symmetry-breaking factors in various physical systems. We employ various relaxed group convolution architectures to uncover various symmetry-breaking factors that are interpretable and physically meaningful in different physical systems, including the phase transition of crystal structure, the isotropy and homogeneity breaking in turbulent flow, and the time-reversal symmetry breaking in pendulum systems.} }
Endnote
%0 Conference Paper %T Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution %A Rui Wang %A Elyssa Hofgard %A Han Gao %A Robin Walters %A Tess Smidt %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-wang24y %I PMLR %P 50599--50621 %U https://proceedings.mlr.press/v235/wang24y.html %V 235 %X Modeling symmetry breaking is essential for understanding the fundamental changes in the behaviors and properties of physical systems, from microscopic particle interactions to macroscopic phenomena like fluid dynamics and cosmic structures. Thus, identifying sources of asymmetry is an important tool for understanding physical systems. In this paper, we focus on learning asymmetries of data using relaxed group convolutions. We provide both theoretical and empirical evidence that this flexible convolution technique allows the model to maintain the highest level of equivariance that is consistent with data and discover the subtle symmetry-breaking factors in various physical systems. We employ various relaxed group convolution architectures to uncover various symmetry-breaking factors that are interpretable and physically meaningful in different physical systems, including the phase transition of crystal structure, the isotropy and homogeneity breaking in turbulent flow, and the time-reversal symmetry breaking in pendulum systems.
APA
Wang, R., Hofgard, E., Gao, H., Walters, R. & Smidt, T.. (2024). Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:50599-50621 Available from https://proceedings.mlr.press/v235/wang24y.html.

Related Material