On the performance of regularized regression learning in Hilbert space

Authors:
Di-Rong Chen;Han Li
Affiliations:
Department of Mathematics, LMIB, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;Department of Mathematics, LMIB, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
Venue:
Neurocomputing
Year:
2012

Citing 12
Cited 3

The nature of statistical learning theory

The nature of statistical learning theory
Rademacher and gaussian complexities: risk bounds and structural results

The Journal of Machine Learning Research
Support Vector Machine Soft Margin Classifiers: Error Analysis

The Journal of Machine Learning Research
Model Selection for Regularized Least-Squares Algorithm in Learning Theory

Foundations of Computational Mathematics
Learning Rates of Least-Square Regularized Regression

Foundations of Computational Mathematics
Learning Theory: An Approximation Theory Viewpoint (Cambridge Monographs on Applied & Computational Mathematics)

Learning Theory: An Approximation Theory Viewpoint (Cambridge Monographs on Applied & Computational Mathematics)
Support vector machine for functional data classification

Neurocomputing
Learning rates of support vector machine classifier for density level detection

Neurocomputing
Rademacher penalties and structural risk minimization

IEEE Transactions on Information Theory
Compressed sensing

IEEE Transactions on Information Theory
Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?

IEEE Transactions on Information Theory
On the Performance of Clustering in Hilbert Spaces

IEEE Transactions on Information Theory

Error analysis of coefficient-based regularized algorithm for density-level detection

Neural Computation
Universal learning using free multivariate splines

Neurocomputing
Generalization performance of support vector classifiers for density level detection

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Based on m randomly drawn vectors in a separable Hilbert space, we investigate the consistency of the regularized regression learning algorithm by using Rademacher averages techniques. Furthermore, random projection technique for speeding up the regression learning algorithm is used. The learning rates of the regularized regression learning algorithm with random projection are established. Theoretical analysis shows that it is possible to learn directly in the projected domain. Our results reflect a tradeoff between accuracy and computational complexity when one uses regularized least square regression algorithm after random projection of the data to a finite dimensional space.