Large data and zero noise limits of graph-based semi-supervised learning algorithms

DOI10.1016/j.acha.2019.03.005zbMath1442.62768arXiv1805.09450OpenAlexW2963110350WikidataQ128098408 ScholiaQ128098408MaRDI QIDQ778036

Matthew Thorpe, Dejan Slepčev, Matthew M. Dunlop, Andrew M. Stuart

Publication date: 30 June 2020

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

Full work available at URL: https://arxiv.org/abs/1805.09450

zbMATH Keywords

krigingasymptotic consistencyBayesian inferencesemi-supervised learninghigher-order fractional Laplacian

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Bayesian inference (62F15) Bayesian problems; characterization of Bayes procedures (62C10) Learning and adaptive systems in artificial intelligence (68T05) Quadratic programming (90C20) Programming in abstract spaces (90C48) Methods involving semicontinuity and convergence; relaxation (49J45) Statistical aspects of big data and data science (62R07)

Related Items

A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors ⋮ Lipschitz Regularity of Graph Laplacians on Random Data Clouds ⋮ From graph cuts to isoperimetric inequalities: convergence rates of Cheeger cuts on data clouds ⋮ Large data limit for a phase transition model with the p-Laplacian on point clouds ⋮ Harmonic analysis on graphs via Bratteli diagrams and path-space measures ⋮ Improved spectral convergence rates for graph Laplacians on \(\varepsilon \)-graphs and \(k\)-NN graphs ⋮ Partial differential equations and variational methods for geometric processing of images ⋮ Spectral analysis of weighted Laplacians arising in data clustering ⋮ Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors ⋮ Rates of convergence for Laplacian semi-supervised learning with low labeling rates ⋮ Unnamed Item ⋮ Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning ⋮ Properly-weighted graph Laplacian for semi-supervised learning ⋮ Analysis of $p$-Laplacian Regularization in Semisupervised Learning ⋮ Unnamed Item

Uses Software

• PRMLT

Cites Work

• Continuum limit of total variation on point clouds
• Convergence and rates for fixed-interval multiple-track smoothing using \(k\)-means type optimization
• An introduction to \(\Gamma\)-convergence
• Weighted nonlocal Laplacian on interpolation from sparse data
• Riemannian manifolds with maximal eigenfunction growth
• \(\Gamma\)-convergence of graph Ginzburg-Landau functionals
• Consistency of spectral clustering
• The spectral function of an elliptic operator
• Interpolation between weighted L\(^p\)-spaces
• UNIFORM BOUNDS FOR EIGENFUNCTIONS OF THE LAPLACIAN ON MANIFOLDS WITH BOUNDARY*
• Convergence of the $k$-Means Minimization Problem using $\Gamma$-Convergence
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• A First Course in Sobolev Spaces
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• A survey on level set methods for inverse problems and optimal design
• MCMC methods for functions: modifying old algorithms to make them faster
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Large data and zero noise limits of graph-based semi-supervised learning algorithms