Capacity of reproducing kernel spaces in learning theory

Authors:
Ding-Xuan Zhou
Affiliations:
Dept. of Math., City Univ. of Hong Kong, China
Venue:
IEEE Transactions on Information Theory
Year:
2006

Citing 0
Cited 43

Support Vector Machine Soft Margin Classifiers: Error Analysis

The Journal of Machine Learning Research
SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming

Neural Computation
Mercer theorem for RKHS on noncompact sets

Journal of Complexity
Multi-kernel regularized classifiers

Journal of Complexity
Learning Coordinate Covariances via Gradients

The Journal of Machine Learning Research
Learnability of Gaussians with Flexible Variances

The Journal of Machine Learning Research
The covering number for some Mercer kernel Hilbert spaces

Journal of Complexity
Derivative reproducing properties for kernel methods in learning theory

Journal of Computational and Applied Mathematics
Classification with a Reject Option using a Hinge Loss

The Journal of Machine Learning Research
Learning with sample dependent hypothesis spaces

Computers & Mathematics with Applications
Regularized Fitted Q-Iteration: Application to Planning

Recent Advances in Reinforcement Learning
Learning from uniformly ergodic Markov chains

Journal of Complexity
The generalization performance of ERM algorithm with strongly mixing observations

Machine Learning
Gradient learning in a classification setting by gradient descent

Journal of Approximation Theory
Regularized fitted Q-iteration for planning in continuous-space Markovian decision problems

ACC'09 Proceedings of the 2009 conference on American Control Conference
Model-based and model-free reinforcement learning for visual servoing

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Hermite learning with gradient data

Journal of Computational and Applied Mathematics
Mercer theorem for RKHS on noncompact sets

Journal of Complexity
Semisupervised multicategory classification with imperfect model

IEEE Transactions on Neural Networks
Classification with Gaussians and Convex Loss

The Journal of Machine Learning Research
Online Learning with Samples Drawn from Non-identical Distributions

The Journal of Machine Learning Research
Generalization performance of ERM algorithm with geometrically ergodic Markov chain samples

ICNC'09 Proceedings of the 5th international conference on Natural computation
Variable weighted learning algorithm and its convergence rate

ICNC'09 Proceedings of the 5th international conference on Natural computation
Semi-supervised learning based on high density region estimation

Neural Networks
Optimal learning rates for least squares regularized regression with unbounded sampling

Journal of Complexity
Estimation of learning rate of least square algorithm via Jackson operator

Neurocomputing
On complexity issues of online learning algorithms

IEEE Transactions on Information Theory
Logistic classification with varying Gaussians

Computers & Mathematics with Applications
Least square regression with lp-coefficient regularization

Neural Computation
Covering numbers of Gaussian reproducing kernel Hilbert spaces

Journal of Complexity
Full length article: Concentration estimates for the moving least-square method in learning theory

Journal of Approximation Theory
The consistency analysis of coefficient regularized classification with convex loss

WSEAS Transactions on Mathematics
Reproducing kernel banach spaces with the l1 norm ii: Error analysis for regularized least square regression

Neural Computation
Generalization bounds of ERM algorithm with V-geometrically Ergodic Markov chains

Advances in Computational Mathematics
Asymptotic normality of support vector machine variants and other regularized kernel methods

Journal of Multivariate Analysis
Application of integral operator for regularized least-square regression

Mathematical and Computer Modelling: An International Journal
Classification with non-i.i.d. sampling

Mathematical and Computer Modelling: An International Journal
Learning Rates for Regularized Classifiers Using Trigonometric Polynomial Kernels

Neural Processing Letters
An approximation theory approach to learning with l1 regularization

Journal of Approximation Theory
Concentration estimates for learning with unbounded sampling

Advances in Computational Mathematics
Learning theory approach to minimum error entropy criterion

The Journal of Machine Learning Research
Learning performance of coefficient-based regularized ranking

Neurocomputing
Statistical analysis of the moving least-squares method with unbounded sampling

Information Sciences: an International Journal

Quantified Score

Hi-index	754.90

Visualization

Abstract

The capacity of reproducing kernel Hilbert spaces (RKHS) plays an essential role in the analysis of learning theory. Covering numbers and packing numbers of balls of these reproducing kernel spaces are important measurements of this capacity. We first present lower bound estimates for the packing numbers by means of nodal functions. Then we show that if a Mercer kernel is Cs (for some s0 being not an even integer), the RKHS associated with this kernel can be embedded into Cs2/. This gives upper-bound estimates for the covering number concerning Sobolev smooth kernels.Examples and applications to Vγ dimension and Tikhonov (1977) regularization are presented to illustrate the upper- and lower-bound estimates.