The 2002 Wald Memorial Lectures - Population theory for boosting ensembles

• 成果类型: Article
• 署名作者: Breiman, L
• 署名单位: University of California System; University of California Berkeley
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• 发表日期: 2004
• 页码: 1-11
• 关键词: decision trees; algorithms; CLASSIFICATION; regression

摘要

Tree ensembles are looked at in distribution space, that is, the limit case of infinite sample size. It is shown that the simplest kind of trees is complete in D-dimensional L-2(P) space if the number of terminal nodes T is greater than D. For such trees we show that the AdaBoost algorithm gives an ensemble converging to the Bayes risk.