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.

Composite Multiclass Losses

Thumbnail Image

Date

2011

Authors

Vernet, Elodie
Williamson, Robert
Reid, Mark

Journal Title

Journal ISSN

Volume Title

Publisher

Neural Information Processing Systems Foundation

Abstract

We consider loss functions for multiclass prediction problems. We show when a multiclass loss can be expressed as a "proper composite loss", which is the composition of a proper loss and a link function. We extend existing results for binary losses to mul

Description

Keywords

Keywords: Existence and uniqueness; Integral representation; Loss functions; Multi-class; Multiclass prediction; Properness; Stationarity

Citation

URI

http://hdl.handle.net/1885/39622

Collections

ANU Research Publications

Source

Advances in Neural Information Processing Systems 23

Type

Conference paper

Book Title

Entity type

Access Statement

Open Access

License Rights

DOI

Restricted until

Downloads

File
Description
01_Vernet_Composite_Multiclass_Los_2011.pdf (469.95 KB)

DSpace software copyright © 2002-2026 LYRASIS