Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms

• URL: http://arxiv.org/abs/2603.07299v1
• Date: Sat, 07 Mar 2026 17:46:00 GMT
• Title: Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms
• Abstract summary: Continuous symmetries are fundamental to many scientific and learning problems.<n>Existing symmetry discovery approaches typically search directly in the space of transformation generators or rely on learned augmentation schemes.
• Score: 9.80927748311872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continuous symmetries are fundamental to many scientific and learning problems, yet they are often unknown a priori. Existing symmetry discovery approaches typically search directly in the space of transformation generators or rely on learned augmentation schemes. We propose a fundamentally different perspective based on spectral structure. We introduce a framework for discovering continuous one-parameter subgroups using the Generalized Fourier Transform (GFT). Our central observation is that invariance to a subgroup induces structured sparsity in the spectral decomposition of a function across irreducible representations. Instead of optimizing over generators, we detect symmetries by identifying this induced sparsity pattern in the spectral domain. We develop symmetry detection procedures on maximal tori, where the GFT reduces to multi-dimensional Fourier analysis through their irreducible representations. Across structured tasks, including the double pendulum and top quark tagging, we demonstrate that spectral sparsity reliably reveals one-parameter symmetries. These results position spectral analysis as a principled and interpretable alternative to generator-based symmetry discovery.

Related papers

• Symmetry-Twisted Multi-Entropies: Order Parameters for 2D SPT Phases [0.9558392439655014]
  We show that symmetry-protected topological phases (SPTs) can be distinguished by their entanglement properties.<n>We propose a pair of nonlocal order parameters that can detect and distinguish all bosonic SPTs in 2D protected by internal discrete, Abelian unitary symmetries.<n>Our results suggest multipartite entanglement to be a defining feature of SPTs.
  arXiv  Detail & Related papers  (2026-07-13T18:00:01Z)
• Group Invariant Spectral Embedding [2.1538077160255313]
  We show that $G$-invariant spectral embedding recovers the intrinsic geometry of the data, in contrast to standard spectral embedding.<n>We validate our approach on datasets with $mathrmSO(2)$ or $mathrmSO(3)$ symmetry.
  arXiv  Detail & Related papers  (2026-07-09T23:18:39Z)
• Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation [56.361076943802594]
  CanonFlow achieves state-of-the-art performance on the challenging GEOM-DRUG dataset, and the advantage remains large in few-step generation.
  arXiv  Detail & Related papers  (2026-02-16T18:58:55Z)
• Entropic order parameters and topological holography [0.0]
  We show that the symmetry topological field theory (SymTFT) construction provides a natural and intuitive framework for the characterising phases with broken symmetries.<n>In particular, the origin of the distinguishability of the vacua resulting from spontaneously broken non-invertible symmetries is made manifest with an information-theoretic perspective.
  arXiv  Detail & Related papers  (2025-12-30T13:39:00Z)
• Improved Ising Meson Spectroscopy Simulation on a Noisy Digital Quantum Device [0.003004180595230273]
  We show improved spectroscopy of confined excitations using two distinct error-resilient circuit construction techniques.<n>We successfully identify key signatures of $E_8$ symmetry despite hardware noise.
  arXiv  Detail & Related papers  (2025-12-02T08:16:10Z)
• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• Avoided-crossings, degeneracies and Berry phases in the spectrum of quantum noise through analytic Bloch-Messiah decomposition [49.1574468325115]
  "analytic Bloch-Messiah decomposition" provides approach for characterizing dynamics of quantum optical systems.<n>We show that avoided crossings arise naturally when a single parameter is varied, leading to hypersensitivity of the singular vectors.<n>We highlight the possibility of programming the spectral response of photonic systems through the deliberate design of avoided crossings.
  arXiv  Detail & Related papers  (2025-04-29T13:14:15Z)
• Detection of 2D SPT Order with Partial Symmetries [0.0]
  A method of using partial symmetries to distinguish two dimensional symmetry protected topological phases is proposed.<n>The construction exploits the rotational symmetry of the lattice to extract on-site SPT invariants.<n>Its robustness is suggested by interpreting partial symmetries as generating the topological partition functions of lens spaces.
  arXiv  Detail & Related papers  (2025-03-06T14:56:52Z)
• Spectral fluctuations of multiparametric complex matrix ensembles: evidence of a single parameter dependence [0.0]
  We numerically analyze the spectral statistics of the multiparametric Gaussian ensembles of complex matrices with zero mean and variances with different decay routes away from the diagonals. Such ensembles can serve as good models for a wide range of phase transitions e.g. localization to delocalization in non-Hermitian systems or Hermitian to non-Hermitian one.
  arXiv  Detail & Related papers  (2023-12-13T15:21:35Z)
• Accelerated Discovery of Machine-Learned Symmetries: Deriving the Exceptional Lie Groups G2, F4 and E6 [55.41644538483948]
  This letter introduces two improved algorithms that significantly speed up the discovery of symmetry transformations. Given the significant complexity of the exceptional Lie groups, our results demonstrate that this machine-learning method for discovering symmetries is completely general and can be applied to a wide variety of labeled datasets.
  arXiv  Detail & Related papers  (2023-07-10T20:25:44Z)
• Oracle-Preserving Latent Flows [58.720142291102135]
  We develop a methodology for the simultaneous discovery of multiple nontrivial continuous symmetries across an entire labelled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to transformations invariant with respect to high-dimensional oracles.
  arXiv  Detail & Related papers  (2023-02-02T00:13:32Z)
• Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces [52.424621227687894]
  We introduce a unified framework for group equivariant networks on homogeneous spaces. We take advantage of the sparsity of Fourier coefficients of the lifted feature fields. We show that other methods treating features as the Fourier coefficients in the stabilizer subgroup are special cases of our activation.
  arXiv  Detail & Related papers  (2022-06-16T17:59:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.