Skip navigation
Skip navigation

The convexity and design of composite multiclass losses

Reid, Mark; Williamson, Robert; Sun, Peng

Description

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore the implications. We also show how the separation of concerns afforded by using this composite representation allows for the design of families of losses with the same Bayes risk.

CollectionsANU Research Publications
Date published: 2012
Type: Conference paper
URI: http://hdl.handle.net/1885/69149
Source: Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Download

File Description SizeFormat Image
01_Reid_The_convexity_and_design_of_2012.pdf741.65 kBAdobe PDF    Request a copy


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

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator