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 weakclassifier, as well as design the most
effective, in a certain sense, boosting algorithms that assume such
requirements.
Author Information
Indraneel Mukherjee (Princeton University)
Robert E Schapire (MIcrosoft Research)
Robert Schapire received his ScB in math and computer science from Brown University in 1986, and his SM (1988) and PhD (1991) from MIT under the supervision of Ronald Rivest. After a short postdoc at Harvard, he joined the technical staff at AT&T Labs (formerly AT&T Bell Laboratories) in 1991 where he remained for eleven years. At the end of 2002, he became a Professor of Computer Science at Princeton University. His awards include the 1991 ACM Doctoral Dissertation Award, the 2003 GĂ¶del Prize and the 2004 Kanelakkis Theory and Practice Award (both of the last two with Yoav Freund). His main research interest is in theoretical and applied machine learning.
More from the Same Authors

2014 Poster: A DriftingGames Analysis for Online Learning and Applications to Boosting »
Haipeng Luo · Robert E Schapire 
2010 Poster: A Reduction from Apprenticeship Learning to Classification »
Umar Syed · Robert E Schapire 
2010 Poster: A Theory of Multiclass Boosting »
Indraneel Mukherjee · Robert E Schapire 
2010 Poster: NonStochastic Bandit Slate Problems »
Satyen Kale · Lev Reyzin · Robert E Schapire 
2008 Poster: Relative Performance Guarantees for Approximate Inference in Latent Dirichlet Allocation »
Indraneel Mukherjee · David Blei 
2008 Spotlight: Relative Performance Guarantees for Approximate Inference in Latent Dirichlet Allocation »
Indraneel Mukherjee · David Blei 
2007 Oral: A Multiplicative Weights Algorithm for Apprenticeship Learning »
Umar Syed · Robert E Schapire 
2007 Oral: FilterBoost: Regression and Classification on Large Datasets »
Joseph K Bradley · Robert E Schapire 
2007 Poster: FilterBoost: Regression and Classification on Large Datasets »
Joseph K Bradley · Robert E Schapire 
2007 Poster: A Multiplicative Weights Algorithm for Apprenticeship Learning »
Umar Syed · Robert E Schapire 
2007 Tutorial: Theory and Applications of Boosting »
Robert E Schapire