The theory behind the success of adaptive reweighting and combining al- gorithms (arcing) such as Adaboost (Freund & Schapire, 1996a, 1997) and others in reducing generalization error has not been well understood. By formulating prediction as a game where one player makes a selection from instances in the training set and the other a convex linear combina- tion of predictors from a finite set, existing arcing algorithms are shown to be algorithms for finding good game strategies.
展开▼
