Spectral convergence of the connection Laplacian from random samples

DOI10.1093/imaiai/iaw016zbMath1386.94055arXiv1306.1587OpenAlexW2963954124MaRDI QIDQ4603718

Hau-Tieng Wu, Amit Singer

Publication date: 19 February 2018

Published in: Information and Inference (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1306.1587

zbMATH Keywords

principal bundlevector diffusion mapsdiffusion mapsgraph connection Laplacianorientable diffusion mapsvector diffusion distance

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Spectral problems; spectral geometry; scattering theory on manifolds (58J50) Sampling theory in information and communication theory (94A20)

Related Items (35)

Consistency of modularity clustering on random geometric graphs ⋮ Lipschitz Regularity of Graph Laplacians on Random Data Clouds ⋮ Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel ⋮ Ricci curvature and the manifold learning problem ⋮ A Convergent Point Integral Method for Isotropic Elliptic Equations on a Point Cloud ⋮ Unnamed Item ⋮ Improved spectral convergence rates for graph Laplacians on \(\varepsilon \)-graphs and \(k\)-NN graphs ⋮ Graph approximations to the Laplacian spectra ⋮ Unnamed Item ⋮ Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation ⋮ The diffusion geometry of fibre bundles: horizontal diffusion maps ⋮ Approximations of the connection Laplacian spectra ⋮ Certifying global optimality of graph cuts via semidefinite relaxation: a performance guarantee for spectral clustering ⋮ Continuum Limits of Nonlocal $p$-Laplacian Variational Problems on Graphs ⋮ An Escape Time Formulation for Subgraph Detection and Partitioning of Directed Graphs ⋮ Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator ⋮ Modified Virtual Grid Difference for Discretizing the Laplace--Beltrami Operator on Point Clouds ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Manifold embeddings by heat kernels of connection Laplacian ⋮ Spectral convergence of graph Laplacian and heat kernel reconstruction in \(L^\infty\) from random samples ⋮ Harmonic Extension on The Point Cloud ⋮ Unnamed Item ⋮ Point Integral Method for Solving Poisson-Type Equations on Manifolds from Point Clouds with Convergence Guarantees ⋮ Think globally, fit locally under the manifold setup: asymptotic analysis of locally linear embedding ⋮ Convergence of the point integral method for Laplace-Beltrami equation on point cloud ⋮ Embeddings of Riemannian manifolds with finite eigenvector fields of connection Laplacian ⋮ Explore Intrinsic Geometry of Sleep Dynamics and Predict Sleep Stage by Unsupervised Learning Techniques ⋮ A Geometrical Method for Low-Dimensional Representations of Simulations ⋮ Analysis of $p$-Laplacian Regularization in Semisupervised Learning ⋮ A Metric on Directed Graphs and Markov Chains Based on Hitting Probabilities ⋮ Latent common manifold learning with alternating diffusion: analysis and applications ⋮ The SPDE approach to Matérn fields: graph representations ⋮ Data-driven efficient solvers for Langevin dynamics on manifold in high dimensions ⋮ Variational Limits of $k$-NN Graph-Based Functionals on Data Clouds ⋮ Recovering Hidden Components in Multimodal Data with Composite Diffusion Operators

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Alternating projection, ptychographic imaging and phase synchronization
• Embedding Riemannian manifolds by the heat kernel of the connection Laplacian
• Orientability and diffusion maps
• Representation theoretic patterns in three-dimensional cryo-electron microscopy. II: The class averaging problem
• The imbedding problem for Riemannian manifolds
• Embedding Riemannian manifolds by their heat kernel
• Weak convergence and empirical processes. With applications to statistics
• Consistency of spectral clustering
• Diffusion maps
• From graph to manifold Laplacian: the convergence rate
• \(C^1\) isometric imbeddings
• Vector diffusion maps and the connection Laplacian
• Viewing Angle Classification of Cryo-Electron Microscopy Images Using Eigenvectors
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Non-asymptotic analysis of tangent space perturbation
• Local Linear Regression on Manifolds and Its Geometric Interpretation
• A Cheeger Inequality for the Graph Connection Laplacian
• Learning Theory
• Learning Theory
• Graph connection Laplacian methods can be made robust to noise

This page was built for publication: Spectral convergence of the connection Laplacian from random samples