PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Online Passive-Aggressive Algorithms
Koby Crammer, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz and Yoram Singer
NIPS Volume 16, 2003.

Abstract

We present a unified view for {\em online} classification, regression, and uniclass problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the non-realizable case. A conversion of our main online algorithm to the setting of batch learning is also discussed. The end result is new algorithms and accompanying loss bounds for the hinge-loss.

Postscript - Requires a viewer, such as GhostView
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:52
Deposited By:Yoram Singer
Deposited On:14 May 2004