Skip navigation
Skip navigation

Convexity of Proper Composite Binary Losses

Reid, Mark; Williamson, Robert

Description

A composite loss assigns a penalty to a real-valued prediction by associating the prediction with a probability via a link function then applying a class probability estimation (CPE) loss. If the risk for a composite loss is always minimised by predicting the value associated with the true class probability the composite loss is proper. We provide a novel, explicit and complete characterisation of the convexity of any proper composite loss in terms of its link and its \weight function"...[Show more]

CollectionsANU Research Publications
Date published: 2010
Type: Conference paper
URI: http://hdl.handle.net/1885/21866
Source: Proceedings of The 13th International Conference on Artificial Intelligence and Statistics(AISTATS-2010)

Download

File Description SizeFormat Image
01_Reid_Convexity_of_Proper_Composite_2010.pdf1.3 MBAdobe PDF    Request a copy


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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator