A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors

DOI10.1137/19M1245372zbMath1485.35137arXiv1901.10089OpenAlexW3081743041MaRDI QIDQ5037572

Nicolás García Trillos, Ryan W. Murray

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.10089

zbMATH Keywords

nonparametric regressionempirical risk minimizationgraph Laplacian

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Geometric probability and stochastic geometry (60D05) Graph theory (including graph drawing) in computer science (68R10) Laplace operator, Helmholtz equation (reduced wave equation), Poisson equation (35J05) Existence of optimal solutions to problems involving randomness (49J55)

Related Items (5)

Lipschitz Regularity of Graph Laplacians on Random Data Clouds ⋮ From graph cuts to isoperimetric inequalities: convergence rates of Cheeger cuts on data clouds ⋮ A continuum limit for the PageRank algorithm ⋮ Boundary estimation from point clouds: algorithms, guarantees and applications ⋮ Rates of convergence for Laplacian semi-supervised learning with low labeling rates

Uses Software

• SGTlight

Cites Work

• Continuum limit of total variation on point clouds
• Estimating a smooth function on a large graph by Bayesian Laplacian regularisation
• Spectral clustering and the high-dimensional stochastic blockmodel
• A variational approach to the consistency of spectral clustering
• Large data and zero noise limits of graph-based semi-supervised learning algorithms
• A transportation \(L^p\) distance for signal analysis
• On the strong universal consistency of nearest neighbor regression function estimates
• A distribution-free theory of nonparametric regression
• A graph discretization of the Laplace-Beltrami operator
• Properly-weighted graph Laplacian for semi-supervised learning
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature.
• Consistency of spectral clustering
• Adaptive piecewise polynomial estimation via trend filtering
• Diffusion maps
• From graph to manifold Laplacian: the convergence rate
• Maximum principle and uniform convergence for the finite element method
• Total Variation in Imaging
• Consistency of Cheeger and Ratio Graph Cuts
• Nonparametric sparsity and regularization
• A new analytical approach to consistency and overfitting in regularized empirical risk minimization
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• Continuum Limits of Posteriors in Graph Bayesian Inverse Problems
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• Kernel-Based Reconstruction of Graph Signals
• Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps
• The game theoreticp-Laplacian and semi-supervised learning with few labels
• On the measure of Voronoi cells
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• An Introduction to Partial Differential Equations
• Analysis of $p$-Laplacian Regularization in Semisupervised Learning
• Learning Theory and Kernel Machines
• Learning Theory
• Learning Theory
• Diffusion processes in a small time interval
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Nonparametric Estimation, III. Statistically Equivalent Blocks and Multivariate Tolerance Regions--The Discontinuous Case
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors