Generalisation Error Bounds for Classifiers Trained with Interdependent Data

Nicolas Usunier (1) , Massih-Reza Amini (1) , Patrick Gallinari (1)

1 MALIRE - Machine Learning and Information Retrieval

In this paper we propose a general framework to study the generalization properties of binary classifiers trained with data which may be dependent, but are 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.

Domaines: Informatique [cs]

Nicolas Usunier, Massih-Reza Amini, Patrick Gallinari. Generalisation Error Bounds for Classifiers Trained with Interdependent Data. NIPS 2005 - 18th International Conference on Neural Information Processing Systems, Dec 2005, Vancouver, Canada. pp.1369-1376. ⟨hal-01490502⟩