Local Rademacher complexity bounds based on covering numbers

详细信息    查看全文

• 作者：Yunwen Lei^a ; ^b ; ^{yunwen.lei@hotmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Lixin Ding^b ; ^{lxding@whu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yingzhou Bi^a ; ^{byzhou@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Local Rademacher complexity ; Covering numbers ; Learning theory
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 December 2016
• 年：2016
• 卷：218
• 期：Complete
• 页码：320-330
• 全文大小：647 K

文摘

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate complexities with constraints on expected norms to the corresponding ones with constraints on empirical norms. This result is convenient to apply and could yield refined local Rademacher complexity bounds for function classes satisfying general entropy conditions. We demonstrate the power of our complexity bounds by applying them to simplify the derivation of effective generalization error bounds.