Towards a theoretical foundation for Laplacian-based manifold methods

DOI10.1016/j.jcss.2007.08.006zbMath1157.68056OpenAlexW1989368986MaRDI QIDQ959898

Partha Niyogi, Mikhail Belkin

Publication date: 12 December 2008

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcss.2007.08.006

zbMATH Keywords

Laplace-Beltrami operatorgraph Laplacianmanifold methods

Mathematics Subject Classification ID

Random graphs (graph-theoretic aspects) (05C80) Learning and adaptive systems in artificial intelligence (68T05) Spectral problems; spectral geometry; scattering theory on manifolds (58J50)

Related Items (68)

Consistency of modularity clustering on random geometric graphs ⋮ Reconstruction of a Riemannian Manifold from Noisy Intrinsic Distances ⋮ On the Relation of Slow Feature Analysis and Laplacian Eigenmaps ⋮ Approximating coarse Ricci curvature on submanifolds of Euclidean space ⋮ Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel ⋮ Ricci curvature and the manifold learning problem ⋮ Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning ⋮ Spherical Conformal Parameterization of Genus-0 Point Clouds for Meshing ⋮ Vortices on Closed Surfaces ⋮ Unnamed Item ⋮ Smooth function extension based on high dimensional unstructured data ⋮ Spatial-spectral operator theoretic methods for hyperspectral image classification ⋮ Data-driven modeling with fuzzy sets and manifolds ⋮ Time coupled diffusion maps ⋮ Perfect histogram matching PCA for face recognition ⋮ On information plus noise kernel random matrices ⋮ Spectral analysis of weighted Laplacians arising in data clustering ⋮ Data Analytics on Graphs Part III: Machine Learning on Graphs, from Graph Topology to Applications ⋮ Generalization errors of Laplacian regularized least squares regression ⋮ A Cheeger-type inequality on simplicial complexes ⋮ Consistency of Dirichlet Partitions ⋮ Unnamed Item ⋮ Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator ⋮ Entropic Optimal Transport on Random Graphs ⋮ On the regularized Laplacian eigenmaps ⋮ Wavelets on graphs via spectral graph theory ⋮ Dynamical geometry and a persistence \(K\)-theory in noisy point clouds ⋮ Graph connection Laplacian and random matrices with random blocks ⋮ Hodge theory on metric spaces. Appendix by Anthony W. Baker ⋮ Hearing the clusters of a graph: A distributed algorithm ⋮ Approximate Quadrature Measures on Data-Defined Spaces ⋮ A general learning framework using local and global regularization ⋮ Locally discriminative topic modeling ⋮ Spectral clustering and the high-dimensional stochastic blockmodel ⋮ Laplace-Beltrami operator on digital surfaces ⋮ Laplacian spectral basis functions ⋮ Manifold learning with arbitrary norms ⋮ A unified framework for harmonic analysis of functions on directed graphs and changing data ⋮ The Normalized Graph Cut and Cheeger Constant: From Discrete to Continuous ⋮ Nonlinear Laplacian spectral analysis for time series with intermittency and low-frequency variability ⋮ Linear Programming in the Semi-streaming Model with Application to the Maximum Matching Problem ⋮ Unnamed Item ⋮ Coarse Ricci curvature as a function on \({M\times M}\) ⋮ Unnamed Item ⋮ Random Walks on Dense Graphs and Graphons ⋮ Learning sets with separating kernels ⋮ Data-driven Thresholding in Denoising with Spectral Graph Wavelet Transform ⋮ A generalized diffusion frame for parsimonious representation of functions on data defined manifolds ⋮ Eignets for function approximation on manifolds ⋮ Convergence of the point integral method for Laplace-Beltrami equation on point cloud ⋮ A variational approach to the consistency of spectral clustering ⋮ Distributed Control for Spatial Self-Organization of Multi-agent Swarms ⋮ Density estimators of Gaussian type on closed Riemannian manifolds ⋮ Graph-based semi-supervised learning via improving the quality of the graph dynamically ⋮ Hydrodynamic limit of the symmetric exclusion process on a compact Riemannian manifold ⋮ Free-boundary conformal parameterization of point clouds ⋮ A direct approach for function approximation on data defined manifolds ⋮ Distance preserving model order reduction of graph-Laplacians and cluster analysis ⋮ The Steerable Graph Laplacian and its Application to Filtering Image Datasets ⋮ Heat kernel analysis of syntactic structures ⋮ Localized Fourier analysis for graph signal processing ⋮ Dynamics-Adapted Cone Kernels ⋮ Unnamed Item ⋮ A class of Laplacian multiwavelets bases for high-dimensional data ⋮ Representation of functions on big data: graphs and trees ⋮ Variational Limits of $k$-NN Graph-Based Functionals on Data Clouds ⋮ Reproducing Kernel Hilbert Spaces for Parametric Partial Differential Equations ⋮ Continuum limit of total variation on point clouds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Chernoff's theorem and discrete time approximations of Brownian motion on manifolds
• Spectral partitioning works: planar graphs and finite element meshes
• Consistency of spectral clustering
• Finding the homology of submanifolds with high confidence from random samples
• From graph to manifold Laplacian: the convergence rate
• [https://portal.mardi4nfdi.de/wiki/Publication:4337503 Open problems of Paul Erd�s in graph theory]
• Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Learning Theory and Kernel Machines
• Distance Functions and Geodesics on Submanifolds of $\R^d$ and Point Clouds
• Computing persistent homology
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Learning Theory
• Learning Theory

This page was built for publication: Towards a theoretical foundation for Laplacian-based manifold methods