- Access by Xinjiang University
Group-theoretic upper bounds on reconstructability in inverse problems
Phys. Rev. E 114, 034131 – Published 16 September, 2026
DOI: https://doi.org/10.1103/grfc-4yk9
Abstract
Reconstructing the causal structure of physical systems from observational data constitutes a fundamental inverse problem. Here we show that the reconstruction dimension—defined as an upper bound on the number of recoverable components—is determined by the group-representation structure of the observation spaces and reconstruction maps. This formulation provides an explicit and operational characterization of reconstructability and reconstruction dimension, extending ideas that are often understood only intuitively in equivariant representation theory. As a concrete example, we demonstrate the reconstruction of the local velocity-gradient tensor from orientational measurements of particles suspended in flows, where the observation and velocity-gradient tensor spaces form SO(3) representations with constrained equivariant maps between them. Using an SO(3)-equivariant neural network (implemented with e3nn), we show that the reconstructable subspaces predicted by the representation decomposition are qualitatively consistent with those found in practice. Our formulation shows that the representation structure constrains reconstructability by determining an upper bound sector by sector, while our numerical results suggest that the actual saturation of the bound depends on the physics and data geometry. Beyond providing a useful theoretical framework, this work also connects the abstract representation-theoretic structure to concrete inverse reconstruction problems in fluid physics.
Physics Subject Headings (PhySH)
Article Text
References (22)
- A. Hyvärinen, J. Karhunen, and E. Oja, Independent Component Analysis (John Wiley & Sons, New York, 2001).
- D. L. Colton, R. Kress, and R. Kress, Inverse Acoustic and Electromagnetic Scattering Theory (Springer, 1998), Vol. 93.
- F.-G. Wieland, A. L. Hauber, M. Rosenblatt, C. Tönsing, and J. Timmer, On structural and practical identifiability, Curr. Opin. Syst. Biol. 25, 60 (2021).
- M. Heinrich, M. Rosenblatt, F.-G. Wieland, H. Stigter, and J. Timmer, On structural and practical identifiability: Current status and update of results, Curr. Opin. Syst. Biol. 41, 100546 (2025).
- O. J. Maclaren and R. Nicholson, What can be estimated? Identifiability, estimability, causal inference and ill-posed inverse problems, arXiv:1904.02826.
- M. Alvarez, D. Luengo, and N. D. Lawrence, Latent force models, in Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research Vol. 5 (PMLR, Clearwater Beach, FL, 2009), pp. 9–16.
- A. Gallet, S. Rigby, T. Tallman, X. Kong, I. Hajirasouliha, A. Liew, D. Liu, L. Chen, A. Hauptmann, and D. Smyl, Structural engineering from an inverse problems perspective, Proc. R. Soc. A 478, 20210526 (2022).
- Ö. Savaş, On flow visualization using reflective flakes, J. Fluid Mech. 152, 235 (1985).
- G. Gauthier, P. Gondret, and M. Rabaud, Motions of anisotropic particles: Application to visualization of three-dimensional flows, Phys. Fluids 10, 2147 (1998).
- M. V. Dyke, An Album of Fluid Motion (Parabolic press, Stanford, California, 1982).
- I. Arai, T. Itano, and M. Sugihara-Seki, Revisiting visualization of spiral states in a wide-gap spherical Couette flow, Acta Mech. 235, 7441 (2024).
- R. T. Forestano, K. T. Matchev, K. Matcheva, A. Roman, E. B. Unlu, and S. Verner, Identifying the group-theoretic structure of machine-learned symmetries, Phys. Lett. B 847, 138306 (2023).
- S. Batzner, A. Musaelian, L. Sun, M. Geiger, J. P. Mailoa, M. Kornbluth, N. Molinari, T. E. Smidt, and B. Kozinsky, E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials, Nat. Commun. 13, 2453 (2022).
- E. Celledoni, M. J. Ehrhardt, C. Etmann, B. Owren, C.-B. Schönlieb, and F. Sherry, Equivariant neural networks for inverse problems, Inverse Probl. 37, 085006 (2021).
- J. Tang and G. Xu, Group symmetry enables faster optimization in inverse problems, arXiv:2505.13223.
- M. Geiger and T. Smidt, e3nn: Euclidean neural networks, arXiv:2207.09453.
- W. Fulton and J. Harris, Representation Theory: A First Course (Springer Science & Business Media, 2013).
- G. B. Jeffery, The motion of ellipsoidal particles immersed in a viscous fluid, Proc. R. Soc. London Ser. A 102, 161 (1922).
- S. Goto, S. Kida, and S. Fujiwara, Flow visualization using reflective flakes, J. Fluid Mech. 683, 417 (2011).
- I. Arai, T. Itano, and M. Sugihara-Seki, Nonlinear aggregation of phase elements on the unit circle under parametric external fields, J. Phys. Soc. Jpn. 94, 114003 (2025).
- F. Goto, T. Itano, M. Sugihara-Seki, and T. Adachi, Bifurcation aspect of polygonal coherence over transitional Reynolds numbers in wide-gap spherical Couette flow, Phys. Rev. Fluids 6, 113903 (2021).
- I. Arai and T. Itano, Multifrequency phase locking and hyperplane structures in particle orientation, Phys. Rev. E 113, 014206 (2026).
