Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems

Published: 23 Oct 2024, Last Modified: 24 Feb 2025NeurReps 2024 PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: symmetry, invariance, Noether's theorem, stochastic processes, diffusion
TL;DR: Noether's theorem can be applied to noisy dynamical systems, and one gets analogues of energy and momentum conservation
Abstract: Noether's theorem provides a powerful link between continuous symmetries and conserved quantities for systems governed by some variational principle. Perhaps unfortunately, most dynamical systems of interest in neuroscience and artificial intelligence cannot be described by any such principle. On the other hand, nonequilibrium physics provides a variational principle that describes how fairly generic noisy dynamical systems are most likely to transition between two states; in this work, we exploit this principle to apply Noether's theorem, and hence learn about how the continuous symmetries of dynamical systems constrain their most likely trajectories. We identify analogues of the conservation of energy, momentum, and angular momentum, and briefly discuss examples of each in the context of models of decision-making, recurrent neural networks, and diffusion generative models.
Submission Number: 80
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview