MINIMIZATION OF A CLASS OF MATRIX TRACE FUNCTIONS BY MEANS OF REFINED MAJORIZATION

被引：28

作者：

KIERS, HAL

TENBERGE, JMF

机构：

来源：

PSYCHOMETRIKA | 1992年 / 57卷 / 03期

关键词：

TRACE OPTIMIZATION; MAJORIZATION; ALTERNATING LEAST SQUARES;

D O I：

10.1007/BF02295425

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

A procedure is described for minimizing a class of matrix trace functions. The procedure is a refinement of an earlier procedure for minimizing the class of matrix trace functions using majorization. It contains a recently proposed algorithm by Koschat and Swayne for weighted Procrustes rotation as a special case. A number of trial analyses demonstrate that the refined majorization procedure is more efficient than the earlier majorization-based procedure.

引用

页码：371 / 382

页数：12

共 11 条

[1]

BIJLEVELD C, 1987, JUN EUR M PSYCH SOC

[2]

BIJLEVELD CCJ, 1989, EXPLORATORY LINEAR D

[3] FITTING LONGITUDINAL REDUCED-RANK REGRESSION-MODELS BY ALTERNATING LEAST-SQUARES [J].