Adaptive Base Class Boost for Multi-class Classification

We propose abc-boost (adaptive base class boost) for multi-class classification and present abc-mart, an implementation of abcboost, based on the multinomial logit model. The key idea is that, at each boosting iteration, we adaptively and greedily choose a base class. Our experiments on public datasets demonstrate the improvement of abc-mart over the original mart algorithm.

• Type: Journal
• Year: 2008
• Where: CORR
• Authors: Ping Li
• Keywords: Base Class, Base Class Boost, CORR 2008, Education, Multinomial Logit Model