2000 character limit reached
Adaptive Base Class Boost for Multi-class Classification (0811.1250v1)
Published 8 Nov 2008 in cs.LG and cs.IR
Abstract: We develop the concept of ABC-Boost (Adaptive Base Class Boost) for multi-class classification and present ABC-MART, a concrete implementation of ABC-Boost. The original MART (Multiple Additive Regression Trees) algorithm has been very successful in large-scale applications. For binary classification, ABC-MART recovers MART. For multi-class classification, ABC-MART considerably improves MART, as evaluated on several public data sets.