Approximate Minimization of the Regularized Expected Error over Kernel Models

Authors:
Věra Kůrková;Marcello Sanguineti
Affiliations:
Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic;Department of Communications, Computer, and System Sciences (DIST), University of Genoa, 16145 Genova, Italy
Venue:
Mathematics of Operations Research
Year:
2008

Citing 0
Cited 7

The extended Ritz method for functional optimization: overview and applications to single-person and team optimal decision problems

Optimization Methods & Software
On spectral windows in supervised learning from data

Information Processing Letters
Bounds for approximate solutions of Fredholm integral equations using kernel networks

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
2011 Special Issue: Can dictionary-based computational models outperform the best linear ones?

Neural Networks
A meta-learning approach to the regularized learning-Case study: Blood glucose prediction

Neural Networks
Suboptimal Solutions to Team Optimization Problems with Stochastic Information Structure

SIAM Journal on Optimization
Learning with boundary conditions

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Learning from data under constraints on model complexity is studied in terms of rates of approximate minimization of the regularized expected error functional. For kernel models with an increasing number n of kernel functions, upper bounds on such rates are derived. The bounds are of the form a/n+b/√n, where a and b depend on the regularization parameter and on properties of the kernel, and of the probability measure defining the expected error. As a special case, estimates of rates of approximate minimization of the regularized empirical error are derived.