Deterministic error analysis of support vector regression and related regularized kernel methods

MaRDI QIDQ2880966zbMATH OpenFDO

Authors Christian Rieger, Barbara Zwicknagl

Publication date 17 April 2012

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://www.jmlr.org/papers/v10/rieger09a.html

zbMATH Keywords

approximation theoryradial basis functionsreproducing kernel Hilbert spacesampling inequalitySobolev space

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Linear inference, regression (62J99) Computational learning theory (68Q32)

Recommendations

• Estimate of error bounds in the improved support vector regression
• An error correction method for support vector regression
• Error analysis of the kernel regularized regression based on refined convex losses and RKBSs
• Learning errors of linear programming support vector regression
• Asymptotic normality of support vector machine variants and other regularized kernel methods
• Analysis of support vector machines regression
• Deterministic error bounds for kernel-based learning techniques under bounded noise
• The effect of the regularity of the error process on the performance of kernel regression estimators
• Optimal regression rates for SVMs using Gaussian kernels

Cited in

(19)

• Analysis of support vector machines regression
• Distribution-free consistency of empirical risk minimization and support vector regression
• Regularized kernel-based reconstruction in generalized Besov spaces
• Estimate of error bounds in the improved support vector regression
• Deterministic error bounds for kernel-based learning techniques under bounded noise
• Sampling inequalities and support vector machines for Galerkin type data
• 9 Kernel methods for surrogate modeling
• Interpolation and approximation in Taylor spaces
• Improved exponential convergence rates by oversampling near the boundary
• Multiscale support vector approach for solving ill-posed problems
• Convergence guarantees for Gaussian process means with misspecified likelihoods and smoothness
• Sampling and Stability
• Multiscale approximation and reproducing kernel Hilbert space methods
• Reproducing kernel Hilbert spaces for parametric partial differential equations
• Sampling inequalities for sparse grids
• A multiscale support vector regression method on spheres with data compression
• A multiscale RBF method for severely ill-posed problems on spheres
• Learning with varying insensitive loss
• Deterministic error analysis for learning from non-point-evaluation functional data

This page was built for publication: Deterministic error analysis of support vector regression and related regularized kernel methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2880966)