First-order asymptotic expansions for spectral convergence of normalized graph Laplacians constructed from samples on manifolds

2026-11-11来源 arXiv stat.MLEnglish
arXiv:2611.13623v1 Announce Type: cross Abstract: Under i.i.d. uniform sampling from a closed Riemannian manifold embedded in Euclidean space, we derive first-order asymptotic expansions for the eigenvalues and eigenvectors of symmetrically normalized graph Laplacians constructed via Gaussian kernels and provide concentration inequalities for the remainder terms. As a direct consequence, we establish the corresponding weak convergence results. Unlike most related works, our analysis does not impose a multiplicity-one assumption on the eigenvalues, thereby extending the applicability of the framework to general manifolds with potentially nontrivial eigenvalue multiplicities.

原文:https://www.a8q9.cn/en/article/first-order-asymptotic-expansions-for-spectral-convergence-of-normalized-graph-l-82e9d5.html

相关文章