Algorithmic aspects of boosting

Osamu Watanabe

pp. 349-359

in: Setsuo Arikawa, Ayumi Shinohara (eds), Progress in discovery science, Berlin, Springer, 2002

Abstract

We discuss algorithmic aspects of boosting techniques, such as Majority Vote Boosting [Fre95], AdaBoost [FS97], and MadaBoost [DW00a]. Considering a situation where we are given a huge amount of examples and asked to find some rule for explaining these example data, we show some reasonable algorithmic approaches for dealing with such a huge dataset by boosting techniques. Through this example, we explain how to use and how to implement "adaptivity" for scaling-up existing algorithms.