An Improved Bregman k-means++ Algorithm via Local Search - 文章详情页

作者：

Tian, Xiaoyun (Tian, Xiaoyun.) | Xu, Dachuan (Xu, Dachuan.) (学者：徐大川) | Guo, Longkun (Guo, Longkun.) | Wu, Dan (Wu, Dan.)

收录：

摘要：

In　this　paper,　we　study　the　Bregman　k-means　problem　with　respect　to-similar　Bregman　divergences　(BKMP).　Given　an　n-point　set　and　BKMP　is　to　find　a　center　subset　with　and　separate　the　given　set　into　k　clusters　accordingly,　aiming　to　minimize　the　sum　of　similar　Bregman　divergences　of　the　points　in　to　their　nearest　centers.　We　propose　a　new　variant　of　k-means++　by　employing　the　local　search　scheme,　and　show　the　algorithm　deserves　a　constant　approximation　guarantee.　©　2020,　Springer　Nature　Switzerland　AG.

关键词：

Approximation algorithms Combinatorial mathematics K-means clustering Local search (optimization)

作者机构：

[ 1 ] [Tian, Xiaoyun]Department of Operations Research and Information Engineering, Beijing University of Technology, Beijing; 100124, China
[ 2 ] [Xu, Dachuan]Department of Operations Research and Information Engineering, Beijing University of Technology, Beijing; 100124, China
[ 3 ] [Guo, Longkun]Shandong Key Laboratory of Computer Networks, School of Computer Science and Technology, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), Jinan; 250353, China
[ 4 ] [Wu, Dan]School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang; 471023, China

通讯作者信息：

[guo, longkun]shandong key laboratory of computer networks, school of computer science and technology, shandong computer science center, qilu university of technology (shandong academy of sciences), jinan; 250353, china

电子邮件地址：

longkun.guo@gmail.com

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至