Usunier, Nicolas
Generalization error bounds for classifiers trained with interdependent data
Usunier, Nicolas, Amini, Massih-reza, Gallinari, Patrick
In this paper we propose a general framework to study the generalization properties of binary classifiers trained with data which may be dependent, butare deterministically generated upon a sample of independent examples. It provides generalization bounds for binary classification and some cases of ranking problems, and clarifies the relationship between these learning tasks.