一种新的求解CQSDP的全-Newton步内点算法  

A New Full-Newton Step Interior-point Algorithm for Convex Quadratic Semi-definite Programming

作　　者：李鑫[1] 季萍[1] 张明望[1] 

机构地区：[1]三峡大学理学院,湖北宜昌443002

出　　处：《重庆三峡学院学报》2015年第3期31-35,共5页Journal of Chongqing Three Gorges University

基　　金：国家自然科学基金(71471102)阶段性成果

摘　　要：对凸二次半定规划提出了一种新的全-Newton步原始-对偶内点算法.通过建立和应用一些新的技术性结果,证明了算法的迭代复杂性为O(nlogn/ε),这与目前凸二次半定规划的小步校正内点算法最好的迭代复杂性一致.In this paper, we propose a new full-Newton step primal-dual interior-point algorithm for solving convex quadratic semi-definite programming. By establishing and using new technical results, we show that theiteration complexity of algorithm as O（√nlogn/ε）is as good as the currently best iteration complexity forsmall-update interior-point algorithms of convex quadratic semi-definite programming.

关 键 词：凸二次半定规划 内点算法 全-Newton步 迭代复杂性 

分 类 号：G812.78[文化科学—体育学]