Uniform Convergence of Adaptive Graph-Based Regularization

DOI10.1007/11776420_7MaRDI QIDQ5307558zbMATH OpenOpenAlexFDO

Authors Matthias Hein

Publication date 14 September 2007

Published in Learning Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/11776420_7

Mathematics Subject Classification ID

Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Random graphs (graph-theoretic aspects) (05C80) Computational learning theory (68Q32) Combinatorial probability (60C05)

Recommendations

• Graph Laplacians and their convergence on random neighborhood graphs
• Learning Theory
• Learning Theory
• Towards a theoretical foundation for Laplacian-based manifold methods
• From graph to manifold Laplacian: the convergence rate

Cited in

(17)

• Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation
• The game theoretic p-Laplacian and semi-supervised learning with few labels
• Density estimation on manifolds with boundary
• Concentration of kernel matrices with application to kernel spectral clustering
• Consistency of fractional graph-Laplacian regularization in semisupervised learning with finite labels
• Analysis of p-Laplacian regularization in semisupervised learning
• Discrete-to-continuum rates of convergence for nonlocal p-Laplacian evolution problems
• Continuum limits of nonlocal p-Laplacian variational problems on graphs
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• Spatiotemporal analysis using Riemannian composition of diffusion operators
• Hearing the clusters of a graph: A distributed algorithm
• Optimality of spectral clustering in the Gaussian mixture model
• Spectral convergence of symmetrized graph Laplacian on manifolds with boundary
• The SPDE approach to Matérn fields: graph representations
• Spectral clustering and the high-dimensional stochastic blockmodel
• On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
• Spectral convergence of graph Laplacian and heat kernel reconstruction in L^ from random samples

This page was built for publication: Uniform Convergence of Adaptive Graph-Based Regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5307558)