New multicategory boosting algorithms based on multicategory fisher-consistent losses

Hui Zou, Ji Zhu, Trevor Hastie

Research output: Contribution to journalArticlepeer-review

66 Scopus citations

Abstract

Fisher-consistent loss functions play a fundamental role in the construction of successful binary margin-based classifiers. In this paper we establish the Fisher-consistency condition for multicategory classification problems. Our approach uses the margin vector concept which can be regarded as a multicategory generalization of the binary margin. We characterize a wide class of smooth convex loss functions that are Fisher-consistent for multicategory classification. We then consider using the margin-vector-based loss functions to derive multicategory boosting algorithms. In particular, we derive two new multicategory boosting algorithms by using the exponential and logistic regression losses.

Original languageEnglish (US)
Pages (from-to)1290-1306
Number of pages17
JournalAnnals of Applied Statistics
Volume2
Issue number4
DOIs
StatePublished - Dec 2008

Keywords

  • Boosting
  • Fisher-consistent losses
  • Multicategory classification

Fingerprint Dive into the research topics of 'New multicategory boosting algorithms based on multicategory fisher-consistent losses'. Together they form a unique fingerprint.

Cite this