摘要
针对计算最小体积闭包椭球(MVEE)的积极集算法中原初始化策略耗时较多的问题,先给出一个基于样本协方差矩阵构造的新初始化策略,然后将该初始化策略应用于秩-2更新算法中,并给出一个计算MVEE改进的积极集算法.数值实验结果表明,基于新的初始化策略的积极集算法能有效提高求解大规模数据集MVEE问题的计算效率.
Aiming at the problem that the original initialization strategy of the active-set algorithm took more time to compute minimum volume enclosing ellipsoid（MVEE）.Firstly,we gave a new initialization strategy based on sample covariance matrix.Secondly,we applied the initialization strategy to the rank-two update algorithm,and gave a modified active-set algorithm to compute MVEE.The results of numerical experiments show that active-set algorithm based on the new initialization strategy can effectively improve the computational efficiency of solving the MVEE problem of large-scale date sets.
作者
丛伟杰
何磊
CONG Weijie HE Lei(School of Science, Xi＇ an University of Posts and Telecommunications, Xi＇ an 710121, China)
出处
《吉林大学学报（理学版）》
CAS
CSCD
北大核心
2017年第5期1141-1145,共5页
Journal of Jilin University:Science Edition
基金
国家自然科学基金(批准号:11601420
11301415)
陕西省教育厅专项科研计划项目(批准号:15JK1651)
关键词
最小体积闭包椭球
初始化策略
积极集
样本协方差矩阵
大规模数据集
minimum volume enclosing ellipsoid
initialization strategy
active-set
sample covariance matrix
large-scale date set
