Generalisation Error Bounds for Classifiers Trained with Interdependent Data
Nicolas Usunier, Massih Amini and Patrick Gallinari
In: NIPS 2005, 3 Dec - 10 Dec 2005, Vancouver, Canada.

Abstract

In this paper we propose a general framework to study the generalisation properties of binary classifiers trained with data which may be dependent, but are deterministically generated upon a sample of independent samples. It provides generalisation bounds for binary classification and some cases of ranking problems, and clarifies the relationship between these learning tasks.

[Edit]