nips nips2011 nips2011-59 nips2011-59-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Elodie Vernet, Mark D. Reid, Robert C. Williamson
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 multiclass losses. We determine the stationarity condition, Bregman representation, order-sensitivity, existence and uniqueness of the composite representation for multiclass losses. We subsume existing results on “classification calibration” by relating it to properness and show that the simple integral representation for binary proper losses can not be extended to multiclass losses. 1