Adaptive Symmetry Discovery for Dynamical System Identification
Behrooz Tahmasebi, Melanie Weber
cs.LG, cs.AI, math.DS
Submitted: 2026-08-08
Updated: 2026-08-11
Comments: 38 pages, 1 figure. Published at ICML 2026
Journal ref: International Conference on Machine Learning (ICML) 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Dynamical systems model trajectory data generated by fixed underlying dynamics, with applications ranging from biology to physics.
Terminology
Abstract
Dynamical systems model trajectory data generated by fixed underlying dynamics, with applications ranging from biology to physics. Especially in scientific settings, dynamical systems are not generic but often exhibit symmetries imposed by physical laws, formalized through equivariance with respect to group actions. The identification problem concerns recovering the parameters of a system from observed trajectories. In this work, we study adaptive symmetry discovery for dynamical system identification and address how a system can be identified from a single trajectory when it is equivariant with respect to an unknown symmetry group. To this end, we first show that for known symmetries, the system can be identified from a significantly shorter single trajectory than in the generic setting, and we precisely characterize this improvement. We then consider the automatic symmetry discovery setting, proposing a method to learn the symmetry group directly from a single trajectory and incorporate it into the identification procedure, achieving the same optimal trajectory length as in the known-symmetry case. Our analysis relies on tools from group representation theory and the expander properties of Cayley graphs, and may be of independent interest for the study of symmetries in dynamical systems.
Sources
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Learning finite symmetry groups of dynamical systems via equivariance detection
- Almost Optimal Agnostic Control of Unknown Linear Dynamics
- Research Program: Theory of Learning in Dynamical Systems
- Governing Equation Discovery from Data Based on Differential Invariants
- Learning Equivariant Functions via Quadratic Forms
- A model-free method for discovering symmetry in differential equations
- Discovering Symmetry Groups with Flow Matching
- LieAugmenter: Equivariant Learning by Discovering Symmetries with Learnable Augmentations
- Continuous Symmetry Discovery and Enforcement Using Infinitesimal Generators of Multi-parameter Group Actions
- Control-Oriented System Identification: Classical, Learning, and Physics-Informed Approaches
- Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
- Discovering Symbolic Differential Equations with Symmetry Invariants
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks