A PRIMAL-DUAL ACCELERATION ALGORITHM FOR MATRIX COMPLETION PROBLEMS
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
万方数据
Matrix completion has a wide application in many areas such as ma-chine learning,image processing,and computer vision.The primal-dual algorithm is one of the classic algorithms for solving matrix completion problems.However,when solving large-scale matrix completion problems,the efficiency of this primal-dual algorithm is still needed to be further improved.Therefore,on the basis of the primal-dual algorithm framework,this paper improves the efficiency of the al-gorithm through the correction technique,and proposes a primal-dual acceleration algorithm by adding a correction step.Under reasonable assumptions,its global convergence is proved.Finally,numerical experiments are carried out to verify its effectiveness.
NETL
NSTL
万方数据
