A theory of multiclass boosting

Indraneel Mukherjee, Robert E. Schapire

Research output: Contribution to journalArticlepeer-review

65 Scopus citations


Boosting combines weak classifiers to form highly accurate predictors. Although the case of binary classification is well understood, in the multiclass setting, the "correct" requirements on the weak classifier, or the notion of the most efficient boosting algorithms are missing. In this paper, we create a broad and general framework, within which we make precise and identify the optimal requirements on the weak-classifier, as well as design the most effective, in a certain sense, boosting algorithms that assume such requirements.

Original languageEnglish (US)
Pages (from-to)437-497
Number of pages61
JournalJournal of Machine Learning Research
Issue number1
StatePublished - Feb 1 2013

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence


  • Boosting
  • Drifting games
  • Multiclass
  • Weak learning condition


Dive into the research topics of 'A theory of multiclass boosting'. Together they form a unique fingerprint.

Cite this