Spectral convergence of the connection Laplacian from random samples

Abstract

Spectral methods that are based on eigenvectors and eigenvalues of discrete graph Laplacians, such as DiffusionMaps and Laplacian Eigenmaps, are often used for manifold learning and nonlinear dimensionality reduction. It was previously shown by Belkin&Niyogi (2007, Convergence of Laplacian eigenmaps, vol. 19. Proceedings of the 2006 Conference on Advances… (More)

Topics

Cite this paper

@inproceedings{Singer2013SpectralCO, title={Spectral convergence of the connection Laplacian from random samples}, author={Amit Singer and Hau-tieng Wu}, year={2013} }