SVM LEARNING AND Lp APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS

DOI10.1142/S0219530509001384zbMATH Open1175.68346OpenAlexW4233058794WikidataQ115245537 ScholiaQ115245537MaRDI QIDQ3395345FDOQ3395345

Authors: Gui-Bo Ye, Ding-Xuan Zhou 

Publication date: 26 August 2009

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219530509001384

Recommendations

• Learning and approximation by Gaussians on Riemannian manifolds
• Fast rates for support vector machines using Gaussian kernels
• Adaptive learning rates for support vector machines working on data with low intrinsic dimension
• Learning rates for classification with Gaussian kernels
• Learning Theory

zbMATH Keywords

manifold learningreproducing kernel Hilbert spacesapproximationGaussian kernelsgeneral loss functionmulti-kernel regularized classifier

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Methods of global Riemannian geometry, including PDE methods; curvature restrictions (53C21)

Cites Work

• Regularization networks and support vector machines
• Learning Theory
• Consistency of spectral clustering
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Sobolev spaces on Riemannian manifolds
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• Semi-supervised learning on Riemannian manifolds
• Learning and approximation by Gaussians on Riemannian manifolds
• The covering number in learning theory
• Learning theory estimates via integral operators and their approximations
• Capacity of reproducing kernel spaces in learning theory
• Multi-kernel regularized classifiers
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Model selection for regularized least-squares algorithm in learning theory
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Fully online classification by regularization
• Learning theory: from regression to classification

Cited In (12)

• Normal estimation on manifolds by gradient learning.
• Concentration estimates for the moving least-square method in learning theory
• Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
• Learning and approximation by Gaussians on Riemannian manifolds
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Title not available (Why is that?)
• ERM learning algorithm for multi-class classification
• Convergence rate of kernel canonical correlation analysis
• Intrinsic dimension adaptive partitioning for kernel methods
• Solving PDEs on spheres with physics-informed convolutional neural networks
• Adaptive learning rates for support vector machines working on data with low intrinsic dimension
• Integral operator approach to learning theory with unbounded sampling

This page was built for publication: SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3395345)