Towards Spectral Convergence of Locally Linear Embedding on Manifolds with Boundary

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Lyons, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915105719975936
author Lyons, Andrew
author_facet Lyons, Andrew
contents We study the eigenvalues and eigenfunctions of a differential operator that governs the asymptotic behavior of the unsupervised learning algorithm known as Locally Linear Embedding when a large data set is sampled from an interval or disc. In particular, the differential operator is of second order, mixed-type, and degenerates near the boundary. We show that a natural regularity condition on the eigenfunctions imposes a consistent boundary condition and use the Frobenius method to estimate pointwise behavior. We then determine the limiting sequence of eigenvalues analytically and compare them to numerical predictions. Finally, we propose a variational framework for determining eigenvalues on other compact manifolds.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Spectral Convergence of Locally Linear Embedding on Manifolds with Boundary
Lyons, Andrew
Analysis of PDEs
Machine Learning
35J20, 35M12
We study the eigenvalues and eigenfunctions of a differential operator that governs the asymptotic behavior of the unsupervised learning algorithm known as Locally Linear Embedding when a large data set is sampled from an interval or disc. In particular, the differential operator is of second order, mixed-type, and degenerates near the boundary. We show that a natural regularity condition on the eigenfunctions imposes a consistent boundary condition and use the Frobenius method to estimate pointwise behavior. We then determine the limiting sequence of eigenvalues analytically and compare them to numerical predictions. Finally, we propose a variational framework for determining eigenvalues on other compact manifolds.
title Towards Spectral Convergence of Locally Linear Embedding on Manifolds with Boundary
topic Analysis of PDEs
Machine Learning
35J20, 35M12
url https://arxiv.org/abs/2501.09572