Skip navigation
Skip navigation

Information, Divergence and Risk for Binary Experiments

Reid, Mark; Williamson, Robert


We unify f-divergences, Bregman divergences, surrogate regret bounds, proper scoring rules, cost curves, ROC-curves and statistical information. We do this by systematically studying integral and variational representations of these objects and in so doing identify their representation primitives which all are related to cost-sensitive binary classification. As well as developing relationships between generative and discriminative views of learning, the new machinery leads to tight and more...[Show more]

CollectionsANU Research Publications
Date published: 2011
Type: Journal article
Source: Journal of Machine Learning Research
Access Rights: Open Access


File Description SizeFormat Image
01_Reid_Information,_Divergence_and_2011.pdf1.47 MBAdobe PDF

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator