Learnability of Gaussians with flexible variances

zbMATH Open1222.68339MaRDI QIDQ3174075FDOQ3174075

Ding-Xuan Zhou, Yiming Ying

Publication date: 12 October 2011

Full work available at URL: http://www.jmlr.org/papers/v8/ying07a.html

Recommendations

• Online classification with varying Gaussians
• The optimal solution of multi-kernel regularization learning
• Unregularized online algorithms with varying Gaussians
• Classification with Gaussians and convex loss
• Distributed regularized least squares with flexible Gaussian kernels

zbMATH Keywords

learning theoryGaussian kernelregularization schemeGlivenko-Cantelli classempirical covering numberflexible variances

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (37)

• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
• Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions
• Title not available (Why is that?)
• Convergence analysis of online algorithms
• Nonlinear approximation using Gaussian kernels
• A Note on Support Vector Machines with Polynomial Kernels
• Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
• Learning and approximation by Gaussians on Riemannian manifolds
• Error analysis on regularized regression based on the maximum correntropy criterion
• Learnability with respect to fixed distributions
• On extension theorems and their connection to universal consistency in machine learning
• Error bounds for \(l^p\)-norm multiple kernel learning with least square loss
• Multi-kernel regularized classifiers
• Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem
• Distributed regularized least squares with flexible Gaussian kernels
• Orthogonality from disjoint support in reproducing kernel Hilbert spaces
• Unregularized online algorithms with varying Gaussians
• The optimal solution of multi-kernel regularization learning
• Convergence of online pairwise regression learning with quadratic loss
• Approximation of kernel matrices by circulant matrices and its application in kernel selection methods
• High order Parzen windows and randomized sampling
• Summation of Gaussian shifts as Jacobi's third theta function
• Learning performance of regularized regression with multiscale kernels based on Markov observations
• Conditional quantiles with varying Gaussians
• Learning with sample dependent hypothesis spaces
• Parzen windows for multi-class classification
• Optimal regression rates for SVMs using Gaussian kernels
• Quantitative convergence analysis of kernel based large-margin unified machines
• Error Estimates for Multivariate Regression on Discretized Function Spaces
• Learning the coordinate gradients
• Learning Rates for Classification with Gaussian Kernels
• Maximum correntropy criterion regression models with tending-to-zero scale parameters
• Optimal learning with Gaussians and correntropy loss
• Least square regularized regression for multitask learning
• Online Classification with Varying Gaussians
• Error bounds for learning the kernel
• Learning rates of multi-kernel regularized regression

This page was built for publication: Learnability of Gaussians with flexible variances

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174075)