On spectral windows in supervised learning from data

Authors:
Giorgio Gnecco;Marcello Sanguineti
Affiliations:
Department of Communications, Computer, and System Sciences (DIST), University of Genoa, Via Opera Pia 13, 16145 Genova, Italy;Department of Communications, Computer, and System Sciences (DIST), University of Genoa, Via Opera Pia 13, 16145 Genova, Italy
Venue:
Information Processing Letters
Year:
2010

Citing 10
Cited 0

An introduction to computational learning theory

An introduction to computational learning theory
Support-Vector Networks

Machine Learning
An equivalence between sparse approximation and support vector machines

Neural Computation
Learning from Examples as an Inverse Problem

The Journal of Machine Learning Research
Spectral algorithms for supervised learning

Neural Computation
Accuracy of suboptimal solutions to kernel principal component analysis

Computational Optimization and Applications
Approximate Minimization of the Regularized Expected Error over Kernel Models

Mathematics of Operations Research
Learning with generalization capability by kernel methods of bounded complexity

Journal of Complexity
Regularization techniques and suboptimal solutions to optimization problems in learning from data

Neural Computation
On the eigenspectrum of the gram matrix and the generalization error of kernel-PCA

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.89

Visualization

Abstract

For Tikhonov regularization in supervised learning from data, the effect on the regularized solution of a joint perturbation of the regression function and the data is investigated. Spectral windows in the finite-sample and population cases are compared via probabilistic estimates of the differences between regularized solutions.