Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation

by   Xiuyuan Cheng, et al.

This work studies the spectral convergence of graph Laplacian to the Laplace-Beltrami operator when the graph affinity matrix is constructed from N random samples on a d-dimensional manifold embedded in a possibly high dimensional space. By analyzing Dirichlet form convergence and constructing candidate approximate eigenfunctions via convolution with manifold heat kernel, we prove that, with Gaussian kernel, one can set the kernel bandwidth parameter ϵ∼ (log N/ N)^1/(d/2+2) such that the eigenvalue convergence rate is N^-1/(d/2+2) and the eigenvector convergence in 2-norm has rate N^-1/(d+4); When ϵ∼ N^-1/(d/2+3), both eigenvalue and eigenvector rates are N^-1/(d/2+3). These rates are up to a log N factor and proved for finitely many low-lying eigenvalues. The result holds for un-normalized and random-walk graph Laplacians when data are uniformly sampled on the manifold, as well as the density-corrected graph Laplacian (where the affinity matrix is normalized by the degree matrix from both sides) with non-uniformly sampled data. As an intermediate result, we prove new point-wise and Dirichlet form convergence rates for the density-corrected graph Laplacian. Numerical results are provided to verify the theory.


page 30

page 35


Bi-stochastically normalized graph Laplacian: convergence to manifold Laplacian and robustness to outlier noise

Bi-stochastic normalization of kernelized graph affinity matrix provides...

Convergence of Graph Laplacian with kNN Self-tuned Kernels

Kernelized Gram matrix W constructed from data points {x_i}_i=1^N as W_i...

Spectral Convergence of Symmetrized Graph Laplacian on manifolds with boundary

We study the spectral convergence of a symmetrized Graph Laplacian matri...

Diffusion based Gaussian process regression via heat kernel reconstruction

We propose an algorithm for Gaussian Process regression on an unknown em...

Heat kernel coupling for multiple graph analysis

In this paper, we introduce heat kernel coupling (HKC) as a method of co...

Strong uniform convergence of Laplacians of random geometric and directed kNN graphs on compact manifolds

Consider n points independently sampled from a density p of class 𝒞^2 on...

Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling

The Gaussian kernel and its traditional normalizations (e.g., row-stocha...

Please sign up or login with your details

Forgot password? Click here to reset