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

摘要

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.