The golden chain - Rejoinder

• 成果类型: Editorial Material
• 署名作者: Zhang, T
• 署名单位: International Business Machines (IBM); IBM USA
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• 发表日期: 2004
• 页码: 128-134
• 关键词: Classification

摘要

The discussants contributed different views on several aspects of large margin classification methods and outlined some interesting future directions. I would like to thank them for the stimulating comments. In the following I will mainly focus on two issues. One is the conditional probability modeling aspect of large margin classification methods and the other is related to properties of greedy algorithms used in boosting procedures.