Accelerate Vector Diffusion Maps by Landmarks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yeh, Sing-Yuan, Wu, Yi-An, Wu, Hau-Tieng, Tsui, Mao-Pei
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908905730211840
author Yeh, Sing-Yuan
Wu, Yi-An
Wu, Hau-Tieng
Tsui, Mao-Pei
author_facet Yeh, Sing-Yuan
Wu, Yi-An
Wu, Hau-Tieng
Tsui, Mao-Pei
contents We propose a landmark-constrained algorithm, LA-VDM (Landmark Accelerated Vector Diffusion Maps), to accelerate the Vector Diffusion Maps (VDM) framework built upon the Graph Connection Laplacian (GCL), which captures pairwise connection relationships within complex datasets. LA-VDM introduces a novel two-stage normalization that effectively address nonuniform sampling densities in both the data and the landmark sets. Under a manifold model with the frame bundle structure, we show that we can accurately recover the parallel transport with landmark-constrained diffusion from a point cloud, and hence asymptotically LA-VDM converges to the connection Laplacian. The performance and accuracy of LA-VDM are demonstrated through experiments on simulated datasets and an application to nonlocal image denoising.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21247
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Accelerate Vector Diffusion Maps by Landmarks
Yeh, Sing-Yuan
Wu, Yi-An
Wu, Hau-Tieng
Tsui, Mao-Pei
Machine Learning
Differential Geometry
Data Analysis, Statistics and Probability
58J50, 53C05, 53C21, 62M15, 57R40, 57M50
We propose a landmark-constrained algorithm, LA-VDM (Landmark Accelerated Vector Diffusion Maps), to accelerate the Vector Diffusion Maps (VDM) framework built upon the Graph Connection Laplacian (GCL), which captures pairwise connection relationships within complex datasets. LA-VDM introduces a novel two-stage normalization that effectively address nonuniform sampling densities in both the data and the landmark sets. Under a manifold model with the frame bundle structure, we show that we can accurately recover the parallel transport with landmark-constrained diffusion from a point cloud, and hence asymptotically LA-VDM converges to the connection Laplacian. The performance and accuracy of LA-VDM are demonstrated through experiments on simulated datasets and an application to nonlocal image denoising.
title Accelerate Vector Diffusion Maps by Landmarks
topic Machine Learning
Differential Geometry
Data Analysis, Statistics and Probability
58J50, 53C05, 53C21, 62M15, 57R40, 57M50
url https://arxiv.org/abs/2603.21247