夏志明Zhiming Xia

教授

 博士生导师  硕士生导师
性别:男
学历:博士研究生毕业
在职信息:在职
所在单位:数学学院
电子邮箱:

论文成果

当前位置: 中文主页 >> 论文成果

Design of Distributed BFGS Algorithm and Large Sample Properties for Parameter Estimation

点击次数:

影响因子:0.0
发表刊物:Acta Mathematicae Applicatae Sinica
关键字:BFGS; distributed; BFGS; estimator; loss function
摘要:Under the distributed condition,in order to reduce the cost of communication,this paper solves problems of the corresponding distributed algorithm design and statistical inference based on the BFGS quasi-Newton method.With lower communication cost,a fast distributed BFGS algorithm is established.The key of this algorithm is to perform a distributed approximate calculation of the step size.It is theoretically proved that when the number of iterations meets some conditions,the BFGS estimator is consistent and asymptotically normal.And we propose a estimation formula of variance.The experiment verifies the correctness of the basic theory in this article.At the same time it is showed that the estimation accuracy of the distributed BFGS method is very close to that of the centralized method,which further illustrates the effectiveness of the method.
论文类型:期刊论文
卷号:45
期号:4
页面范围:578-594
ISSN号:0254-3079
是否译文:
第一作者:Kaiyi Dang
通讯作者:Zhiming Xia