Test environment running 7.6.6

Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

The convexity and design of composite multiclass losses

Thumbnail Image

Date

2012

Authors

Reid, Mark
Williamson, Robert
Sun, Peng

Journal Title

Journal ISSN

Volume Title

Publisher

Conference Organising Committee

Abstract

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.

Description

Keywords

Citation

URI

http://hdl.handle.net/1885/69149

Collections

Open Access Research

Source

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Type

Conference paper

Book Title

Entity type

Access Statement

License Rights

DOI

Restricted until

2037-12-31

Downloads

File
Description
01_Reid_The_convexity_and_design_of_2012.pdf (741.65 KB)

DSpace software copyright © 2002-2026 LYRASIS