Analysis of $p$-Laplacian Regularization in Semisupervised Learning

DOI10.1137/17M115222XzbMath1422.49020arXiv1707.06213OpenAlexW2962701197MaRDI QIDQ5231303

Dejan Slepčev, Matthew Thorpe

Publication date: 26 August 2019

Published in: SIAM Journal on Mathematical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1707.06213

zbMATH Keywords

asymptotic consistencygamma-convergenceregressionlabel propagationsemisupervised learningnonlocal variational problemsPDE on graphs

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Stability and convergence of numerical methods for boundary value problems involving PDEs (65N12) Methods involving semicontinuity and convergence; relaxation (49J45) Variational methods for second-order elliptic equations (35J20) Existence of optimal solutions to problems involving randomness (49J55)

Related Items

A Maximum Principle Argument for the Uniform Convergence of Graph Laplacian Regressors, Lipschitz Regularity of Graph Laplacians on Random Data Clouds, Large data limit for a phase transition model with the p-Laplacian on point clouds, A continuum limit for the PageRank algorithm, Multiscale Elliptic PDE Upscaling and Function Approximation via Subsampled Data, Analysis and algorithms for \(\ell_p\)-based semi-supervised learning on graphs, Improved spectral convergence rates for graph Laplacians on \(\varepsilon \)-graphs and \(k\)-NN graphs, Unnamed Item, Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation, Spectral analysis of weighted Laplacians arising in data clustering, Swarming: hydrodynamic alignment with pressure, Compactness for a class of integral functionals with interacting local and non-local terms, Continuum limit of p-Laplacian evolution problems on graphs: L^q graphons and sparse graphs, Deep limits of residual neural networks, Generalizing \(p\)-Laplacian: spectral hypergraph theory and a partitioning algorithm, A compactness theorem for functions on Poisson point clouds, Rates of convergence for Laplacian semi-supervised learning with low labeling rates, Unnamed Item, Continuum Limits of Nonlocal $p$-Laplacian Variational Problems on Graphs, Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning, Asymptotic behavior of the Dirichlet energy on Poisson point clouds, Mumford–Shah functionals on graphs and their asymptotics, Nodal domain count for the generalized graph \(p\)-Laplacian, Discrete-to-Continuum Limits of Multibody Systems with Bulk and Surface Long-Range Interactions, Asymptotic flatness of Morrey extremals, Continuum limit of Lipschitz learning on graphs, CURE: Curvature Regularization for Missing Data Recovery, Function approximation via the subsampled Poincaré inequality, Loss of Double-Integral Character During Relaxation, Gromov-Hausdorff limit of Wasserstein spaces on point clouds, Properly-weighted graph Laplacian for semi-supervised learning, Analysis of $p$-Laplacian Regularization in Semisupervised Learning, Unnamed Item, Iterated Numerical Homogenization for MultiScale Elliptic Equations with Monotone Nonlinearity, Consistency of Lipschitz Learning with Infinite Unlabeled Data and Finite Labeled Data, Variational Limits of $k$-NN Graph-Based Functionals on Data Clouds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Continuum limit of total variation on point clouds
• Fitting a Sobolev function to data. I
• Fitting a Sobolev function to data. III
• A new approach to Sobolev spaces and connections to \(\Gamma\)-convergence
• Semi-supervised learning on Riemannian manifolds
• A variational approach to the consistency of spectral clustering
• Fitting a Sobolev function to data. II.
• Large data and zero noise limits of graph-based semi-supervised learning algorithms
• Minimax grid matching and empirical measures
• Fitting a \(C^m\)-smooth function to data. II
• On optimal matchings
• Tight bounds for minimax grid matching with applications to the average case analysis of algorithms
• An introduction to \(\Gamma\)-convergence
• Consistency of modularity clustering on random geometric graphs
• A transportation \(L^p\) distance for signal analysis
• A graph discretization of the Laplace-Beltrami operator
• Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator
• Nonlinear elliptic partial differential equations and \(p\)-harmonic functions on graphs.
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Nonlocal PDEs on graphs: from tug-of-war games to unified interpolation on images and point clouds
• Fitting a \(C^m\)-smooth function to data. I.
• Fitting a \(C^m\)-smooth function to data. III.
• Consistency of spectral clustering
• Diffusion maps
• From graph to manifold Laplacian: the convergence rate
• 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
• Convergence of the $k$-Means Minimization Problem using $\Gamma$-Convergence
• On the $p$-Laplacian and $\infty$-Laplacian on Graphs with Applications in Image and Data Processing
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• A non-local anisotropic model for phase transitions: asymptotic behaviour of rescaled energies
• Random Geometric Graphs
• Asymptotic Statistics
• Consistency of Dirichlet Partitions
• Spectral convergence of the connection Laplacian from random samples
• Point Integral Method for Solving Poisson-Type Equations on Manifolds from Point Clouds with Convergence Guarantees
• Analysis of $p$-Laplacian Regularization in Semisupervised Learning
• A Convergent Point Integral Method for Isotropic Elliptic Equations on a Point Cloud
• Uniform Convergence of Adaptive Graph-Based Regularization
• Asymptotic analysis of the Ginzburg–Landau functional on point clouds
• Upper and Lower Bounds for Stochastic Processes
• Operator norm convergence of spectral clustering on level sets
• A Hamilton--Jacobi Equation for the Continuum Limit of Nondominated Sorting
• Learning Theory
• Optimal Transport
• Optimal Lipschitz extensions and the infinity Laplacian