On the performance of kernel classes

Authors:
Shahar Mendelson
Affiliations:
RSISE, The Australian National University, Canberra, ACT 0200, Australia
Venue:
The Journal of Machine Learning Research
Year:
2003

Citing 2
Cited 5

Asymptotic theory of finite dimensional normed spaces

Asymptotic theory of finite dimensional normed spaces
Improving the sample complexity using global data

IEEE Transactions on Information Theory

Diffusion Kernels on Statistical Manifolds

The Journal of Machine Learning Research
Learning Bounds for Kernel Regression Using Effective Data Dimensionality

Neural Computation
Using the doubling dimension to analyze the generalization of learning algorithms

Journal of Computer and System Sciences
Oracle inequalities for support vector machines that are based on random entropy numbers

Journal of Complexity
On the convergence rate of lp-norm multiple kernel learning

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present sharp bounds on the localized Rademacher averages of the unit ball in a reproducing kernel Hilbert space in terms of the eigenvalues of the integral operator associated with the kernel. We use this result to estimate the performance of the empirical minimization algorithm when the base class is the unit ball of the reproducing kernel Hilbert space.