Convexity of Proper Composite Binary Losses
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]
|Collections||ANU Research Publications|
|Source:||Proceedings of The 13th International Conference on Artificial Intelligence and Statistics(AISTATS-2010)|
|01_Reid_Convexity_of_Proper_Composite_2010.pdf||1.3 MB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.