Convexity of Proper Composite Binary Losses

Date

2010

Authors

Reid, Mark
Williamson, Robert

Journal Title

Journal ISSN

Volume Title

Publisher

Society for Artificial Intelligence and Statistics

Abstract

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" associated with its proper CPE loss.

Description

Keywords

Keywords: Class probabilities; Weight functions; Artificial intelligence; Forecasting

Citation

Source

Proceedings of The 13th International Conference on Artificial Intelligence and Statistics(AISTATS-2010)

Type

Conference paper

Book Title

Entity type

Access Statement

License Rights

DOI

Restricted until

2037-12-31