Spectral analysis of weighted Laplacians arising in data clustering

DOI10.1016/j.acha.2021.07.004OpenAlexW3196478790MaRDI QIDQ2667045

Bamdad Hosseini, Assad A. Oberai, Andrew M. Stuart, Franca Hoffmann

Publication date: 23 November 2021

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.06389

zbMATH Keywords

spectral gapdifferential geometryperturbation analysisspectral clusteringgraph Laplacianelliptic differential operatorslarge data limits

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Pattern recognition, speech recognition (68T10) Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Eigenvalue problems for linear operators (47A75) Perturbations in context of PDEs (35B20)

Related Items

A continuum limit for the PageRank algorithm, A novel approach to investigate the stability analysis and the dynamics of reaction-diffusion SVIR epidemic model, Geometric scattering on measure spaces, Unnamed Item

Uses Software

• PETSc
• FEniCS
• SyFi

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Continuum limit of total variation on point clouds
• Automated solution of differential equations by the finite element method. The FEniCS book
• A variational approach to the consistency of spectral clustering
• Large data and zero noise limits of graph-based semi-supervised learning algorithms
• Variable bandwidth diffusion kernels
• Towards a theoretical foundation for Laplacian-based manifold methods
• Data spectroscopy: eigenspaces of convolution operators and clustering
• Variable kernel density estimation
• Phase transitions and metastability in Markovian and molecular systems
• Identification of almost invariant aggregates in reversible nearly uncoupled Markov chains
• Metastability in reversible diffusion processes. I: Sharp asymptotics for capacities and exit times
• Metastability in reversible diffusion processes. II: Precise asymptotics for small eigenvalues
• Perturbation theory for linear operators.
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• The geometry of kernelized spectral clustering
• Consistency of spectral clustering
• Diffusion maps
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• The game theoreticp-Laplacian and semi-supervised learning with few labels
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• Spectral Convergence of Diffusion Maps: Improved Error Bounds and an Alternative Normalization
• Continuum Limits of Nonlocal $p$-Laplacian Variational Problems on Graphs
• Continuum limit of the nonlocal p-Laplacian evolution problem on random inhomogeneous graphs
• Stochastic Processes and Applications
• Analysis of $p$-Laplacian Regularization in Semisupervised Learning
• A Nonparametric Estimate of a Multivariate Density Function