Guarantees for Approximate Incremental SVMs

Nicolas Usunier, Antoine Bordes, Léon Bottou ; JMLR W&CP 9:884-891, 2010.

Abstract

Assume a teacher provides examples one by one. An approximate incremental SVM computes a sequence of classifiers that are close to the true SVM solutions computed on the successive incremental training sets. We show that simple algorithms can satisfy an averaged accuracy criterion with a computational cost that scales as well as the best SVM algorithms with the number of examples. Finally, we exhibit some experiments highlighting the benefits of joining fast incremental optimization and curriculum and active learning (Schon and Cohn, 2000; Bordes et al., 2005; Bengio et al., 2009).