Convergence rate of SVM for kernel-based robust regression

DOI10.1142/S0219691319500048zbMath1408.41015OpenAlexW2896723012WikidataQ129126408 ScholiaQ129126408MaRDI QIDQ4626547

Shuhua Wang, Bao Huai Sheng, Zhen Long Chen

Publication date: 28 February 2019

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219691319500048

zbMATH Keywords

convergence raterobust regressionsupport vector machinequasiconvex loss functionright directional derivative

Mathematics Subject Classification ID

Computational learning theory (68Q32) Convex programming (90C25) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Approximation by other special function classes (41A30)

Related Items (5)

Learning rates of kernel-based robust classification ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Convergence of online pairwise regression learning with quadratic loss ⋮ On the K-functional in learning theory ⋮ Coefficient-based regularization network with variance loss for error

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regularized least square regression with unbounded and dependent sampling
• Integral operator approach to learning theory with unbounded sampling
• Convergence rate of the semi-supervised greedy algorithm
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Estimating conditional quantiles with the help of the pinball loss
• A new comparison theorem on conditional quantiles
• Multi-kernel regularized classifiers
• Generalized convexity and optimization. Theory and applications
• Aspects of robust linear regression
• Homotopy continuation approaches for robust SV classification and regression
• Semi-supervised learning based on high density region estimation
• Generalization errors of Laplacian regularized least squares regression
• Conditional quantiles with varying Gaussians
• Learning sets with separating kernels
• The learning rates of regularized regression based on reproducing kernel Banach spaces
• The convergence rate of semi-supervised regression with quadratic loss
• On the mathematical foundations of learning
• Learning rate of magnitude-preserving regularization ranking with dependent samples
• Half supervised coefficient regularization for regression learning with unbounded sampling
• KERNEL METHODS FOR INDEPENDENCE MEASUREMENT WITH COEFFICIENT CONSTRAINTS
• The performance of semi-supervised Laplacian regularized regression with the least square loss
• The Remedian: A Robust Averaging Method for Large Data Sets
• Support Vector Machines
• Consistency of kernel-based quantile regression
• Robust Truncated Hinge Loss Support Vector Machines
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• The consistency of least-square regularized regression with negative association sequence
• Theory of Reproducing Kernels
• Robust Statistics

This page was built for publication: Convergence rate of SVM for kernel-based robust regression