Large data and zero noise limits of graph-based semi-supervised learning algorithms
From MaRDI portal
(Redirected from Publication:778036)
Bayesian inferencekrigingsemi-supervised learningasymptotic consistencyhigher-order fractional Laplacian
Bayesian inference (62F15) Asymptotic properties of nonparametric inference (62G20) Statistical aspects of big data and data science (62R07) Learning and adaptive systems in artificial intelligence (68T05) Quadratic programming (90C20) Bayesian problems; characterization of Bayes procedures (62C10) Methods involving semicontinuity and convergence; relaxation (49J45) Programming in abstract spaces (90C48)
Abstract: Scalings in which the graph Laplacian approaches a differential operator in the large graph limit are used to develop understanding of a number of algorithms for semi-supervised learning; in particular the extension, to this graph setting, of the probit algorithm, level set and kriging methods, are studied. Both optimization and Bayesian approaches are considered, based around a regularizing quadratic form found from an affine transformation of the Laplacian, raised to a, possibly fractional, exponent. Conditions on the parameters defining this quadratic form are identified under which well-defined limiting continuum analogues of the optimization and Bayesian semi-supervised learning problems may be found, thereby shedding light on the design of algorithms in the large graph setting. The large graph limits of the optimization formulations are tackled through convergence, using the recently introduced metric. The small labelling noise limits of the Bayesian formulations are also identified, and contrasted with pre-existing harmonic function approaches to the problem.
Recommendations
- On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
- Properly-weighted graph Laplacian for semi-supervised learning
- Continuum limit of Lipschitz learning on graphs
- Learning Theory
- Analysis of \(p\)-Laplacian regularization in semisupervised learning
Cites work
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 1522714 (Why is no real title available?)
- scientific article; zbMATH DE number 1865939 (Why is no real title available?)
- scientific article; zbMATH DE number 3239968 (Why is no real title available?)
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- A first course in Sobolev spaces
- A survey on level set methods for inverse problems and optimal design
- An introduction to \(\Gamma\)-convergence
- Consistency of spectral clustering
- Continuum limit of total variation on point clouds
- Convergence and rates for fixed-interval multiple-track smoothing using \(k\)-means type optimization
- Convergence of the \(k\)-means minimization problem using \(\Gamma\)-convergence
- Diffuse Interface Models on Graphs for Classification of High Dimensional Data
- Elliptic problems in nonsmooth domains
- Interpolation between weighted L\(^p\)-spaces
- MCMC methods for functions: modifying old algorithms to make them faster
- On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
- Riemannian manifolds with maximal eigenfunction growth
- The spectral function of an elliptic operator
- UNIFORM BOUNDS FOR EIGENFUNCTIONS OF THE LAPLACIAN ON MANIFOLDS WITH BOUNDARY*
- Weighted nonlocal Laplacian on interpolation from sparse data
- \(\Gamma\)-convergence of graph Ginzburg-Landau functionals
Cited in
(26)- Large data limit for a phase transition model with the p-Laplacian on point clouds
- Partial differential equations and variational methods for geometric processing of images
- Spectral analysis of weighted Laplacians arising in data clustering
- Multilevel approximation of Gaussian random fields: covariance compression, estimation, and spatial prediction
- Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning
- From graph cuts to isoperimetric inequalities: convergence rates of Cheeger cuts on data clouds
- Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors
- Posterior consistency of semi-supervised regression on graphs
- Analysis of \(p\)-Laplacian regularization in semisupervised learning
- Consistency of Lipschitz learning with infinite unlabeled data and finite labeled data
- Plugin estimation of smooth optimal transport maps
- A continuum limit for the PageRank algorithm
- Consistency of fractional graph-Laplacian regularization in semisupervised learning with finite labels
- scientific article; zbMATH DE number 7306882 (Why is no real title available?)
- Harmonic analysis on graphs via Bratteli diagrams and path-space measures
- Lipschitz regularity of graph Laplacians on random data clouds
- A maximum principle argument for the uniform convergence of graph Laplacian regressors
- Rates of convergence for Laplacian semi-supervised learning with low labeling rates
- scientific article; zbMATH DE number 7370580 (Why is no real title available?)
- Continuum limit of Lipschitz learning on graphs
- On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
- Properly-weighted graph Laplacian for semi-supervised learning
- Variational limits of \(k\)-NN graph-based functionals on data clouds
- Mathematical Foundations of Graph-Based Bayesian Semi-Supervised Learning
- The game theoretic \(p\)-Laplacian and semi-supervised learning with few labels
- Improved spectral convergence rates for graph Laplacians on \(\varepsilon \)-graphs and \(k\)-NN graphs
This page was built for publication: Large data and zero noise limits of graph-based semi-supervised learning algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q778036)
