%0 Journal Article
%T Sequential-minimal-optimization algorithm for solving Huber-suppor-vector-regression with non-positive semi-definite kernels<br>求解非半正定核Huber–支持向量回归机问题的序列最小最优化算法
%A ZHOU Xiao-jian
%A MA Yi-zhong
%A ZHU Jia-gang
%A LIU Li-ping
%A WANG Jian-jun
%A <br>周晓剑
%A 马义中
%A 朱嘉钢
%A 刘利平
%A 汪建均
%J 控制理论与应用
%D 2010
%I 
%X Sequential-minimal-optimization(SMO) algorithm is effective in solving large-scale support-vectormachine(SVM) problems. However, the existing algorithms require the kernel functions to be positive definite(PD) or positive semi-definite(PSD), thus limiting their applications. Having considered their deficiencies, we propose a new algorithm for solving Huber-SVR problems with non-positive semi-definite(non-PSD) kernels. This algorithm provides desirable regression-accuracies while ensuring the convergence. Thus, it is of theoretical and practical significance.
%K support-vector-machine
%K non-positive semi-definite kernel
%K sequential-minimal-optimization algorithm
%K Huber-support vector regression<br>支持向量机
%K 非半正定核
%K 序列最小最优化算法
%K Huber–支持向量回归机
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=970898A57DFC021F93AB51667BAED7F7&aid=17AB19B392F0ABECC659B66352FDA59B&yid=140ECF96957D60B2&vid=DB817633AA4F79B9&iid=9CF7A0430CBB2DFD&sid=6EEBEF38C7DFC97E&eid=01A9864A3FFB986F&journal_id=1000-8152&journal_name=控制理论与应用&referenced_num=0&reference_num=14