A Learning Generalization Bound with an Application to Sparse-Representation Classifiers

Authors:
Yoram Gat
Affiliations:
University of California, Berkeley, USA
Venue:
Machine Learning
Year:
2001

Citing 5
Cited 1

Perceptrons: expanded edition

Perceptrons: expanded edition
The nature of statistical learning theory

The nature of statistical learning theory
Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension

Machine Learning
Large margin classification using the perceptron algorithm

COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Generalisation Error Bounds for Sparse Linear Classifiers

COLT '00 Proceedings of the Thirteenth Annual Conference on Computational Learning Theory

A Microchoice Bound for Continuous-Space Classification Algorithms

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

A classifier is said to have good generalization ability if it performs on test data almost as well as it does on the training data. The main result of this paper provides a sufficient condition for a learning algorithm to have good finite sample generalization ability. This criterion applies in some cases where the set of all possible classifiers has infinite VC dimension. The result is applied to prove the good generalization ability of support vector machines by a exploiting a sparse-representation property.