文献类型：会议论文

英文题名：Convergence of coefficient regularized fully online algorithm

作者：Tian, Ming-Dang[1]; Sheng, Bao-Huai[1]

机构：[1] Department of Mathematics, Shaoxing University, Shaoxing, Zhejiang, China

会议论文集：2011 International Conference on Multimedia Technology, ICMT 2011

会议日期：26 July 2011 through 28 July 2011

会议地点：Hangzhou

语种：英文

外文关键词：Binary classification; Convergence analysis; Learning rates; Online algorithm

外文摘要：This paper gives the convergence of coefficient regularized fully online nonsmooth classification algorithm. With the strongly convex loss function based on the Euclidean Space and the parameter λt changes with learning step give a better convergence rate than the usual convex loss functions. ? 2011 IEEE.