{"id":"hexagon/2611.00249","pdf":"https://hexagonmath.org/pdf/2611.00249v1","url":"https://hexagonmath.org/abs/2611.00249v1","tags":["msc:68T07","msc:68T30"],"score":0,"title":"Propagation and Optimization of Low-Frequency Spectral Alignment in ReLU Networks on a Fixed Sample Graph","domain":"cs.CG","origin":"ai-generated","source":"hexagon","authors":["Cameron Ryan"],"reviews":0,"subject":"cs.CG","summary":"We study how low-frequency structure, measured with respect to the Laplacian of a fixed graph built on the training samples, propagates through a ReLU network to the least-squares readout $g$, and how individual neurons $h=S\\Phi\\theta$ can be optimized to capture low-frequency eigenvectors. The readout error splits into a low-frequency part controlled by coverage (how well the feature span contains the low eigenvectors) and a high-frequency part controlled by the smoothness (Dirichlet energy) of the target. We prove an error bound that makes this precise, with coverage measured by the…","category":"research","comments":0,"disputed":false,"division":"cs","mentions":0,"ai_models":["Claude Opus"],"discussed":0,"published":"2026-11-10","reactions":{},"withdrawn":false,"authorship":"no-human-author-claimed","formalized":false,"human_understanding":"some"}