arXiv cs.LG
· Papers
S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs — From Dataset Geometry to Network Weights
arXiv:2606.28444v1 Announce Type: new Abstract: Classical universal approximation theorems establish the expressive power of sigmoidal multilayer perceptrons, but they do not prescribe how initial weights should encode the geometry of a data distribution. We propose S-GAI, a spectral geometry-aware initialization frame