arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1306.1587math.NAcs.NAmath.STstat.MEstat.MLstat.TH
收藏

从随机样本中连接拉普拉斯算子的谱收敛

Spectral Convergence of the connection Laplacian from random samples

Princeton University(普林斯顿大学);University of Toronto(多伦多大学)

Amit Singer, Hau-tieng Wu

AI总结:

本文提出统一框架,利用主纤维结构近似 manifold 上的其他连接拉普拉斯算子,并证明其在无限样本极限下的谱收敛性,适用于非均匀分布和有/无边界的流形。

摘要:

基于离散图拉普拉斯算子的谱方法,如扩散映射和拉普拉斯特征映射,常用于流形学习和非线性降维。Belkin 和 Niyogi 之前证明,在无限多数据点独立采样下,图拉普拉斯的本征向量和本征值收敛到流形的拉普拉斯-贝尔特拉米算子的本征函数和本征值。最近,我们引入了向量扩散映射,展示了流形切丛的连接拉普拉斯算子可通过随机样本近似。本文提出统一框架,通过考虑流形的主纤维结构近似其他连接拉普拉斯算子。我们证明在无限多独立随机样本极限下,这些拉普拉斯算子的本征向量和本征值收敛。我们还推广了谱收敛结果,适用于非均匀分布采样和有/无边界的流形。

英文摘要:

Spectral methods that are based on eigenvectors and eigenvalues of discrete graph Laplacians, such as Diffusion Maps and Laplacian Eigenmaps are often used for manifold learning and non-linear dimensionality reduction. It was previously shown by Belkin and Niyogi \cite{belkin_niyogi:2007} that the eigenvectors and eigenvalues of the graph Laplacian converge to the eigenfunctions and eigenvalues of the Laplace-Beltrami operator of the manifold in the limit of infinitely many data points sampled independently from the uniform distribution over the manifold. Recently, we introduced Vector Diffusion Maps and showed that the connection Laplacian of the tangent bundle of the manifold can be approximated from random samples. In this paper, we present a unified framework for approximating other connection Laplacians over the manifold by considering its principle bundle structure. We prove that the eigenvectors and eigenvalues of these Laplacians converge in the limit of infinitely many independent random samples. We generalize the spectral convergence results to the case where the data points are sampled from a non-uniform distribution, and for manifolds with and without boundary.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑