AI RESEARCH

Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms

arXiv CS.LG

ArXi:2603.07299v1 Announce Type: new 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 develop symmetry detection procedures on maximal tori, where the GFT reduces to multi-dimensional Fourier analysis through their irreducible representations.