ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Classification with Gaussians and Convex Loss

Xiang, Dao-Hong*; Zhou, Ding-Xuan香港城市大学
JOURNAL OF MACHINE LEARNING RESEARCH2009-7
36被引4阅读
引用收藏
分享

摘要

This paper considers binary classification algorithms generated from Tikhonov regularization schemes associated with general convex loss functions and varying Gaussian kernels. Our main goal is to provide fast convergence rates for the excess misclassification error. Allowing varying Gaussian kernels in the algorithms improves learning rates measured by regularization error and sample error. Special structures of Gaussian kernels enable us to construct, by a nice approximation scheme with a Fourier analysis technique, uniformly bounded regularizing functions achieving polynomial decays of the regularization error under a Sobolev smoothness condition. The sample error is estimated by using a projection operator and a tight bound for the covering numbers of reproducing kernel Hilbert spaces generated by Gaussian kernels. The convexity of the general loss function plays a very important role in our analysis.

学科与关键词

关键词
reproducing kernel Hilbert spacebinary classificationgeneral convex lossvarying Gaussian kernelscovering numberapproximation
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
JOURNAL OF MACHINE LEARNING RESEARCH
发表日期
2009-07
卷期
第 10 卷
页码
1447-1468
语言
ENGLISH
成果收录
SCIE
资助标注
Research Grants Council of Hong Kong [CityU 104007]; National Science Fund for Distinguished Young Scholars of China [10529101]

作者

  • X

    Xiang, Dao-Hong (通讯) (第一作者)

    city univ hong kong

  • Z

    Zhou, Ding-Xuan

    city univ hong kong

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417