题名 | Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms |
作者 | |
通讯作者 | Zhang, Zhuo-song |
发表日期 | 2022-08-01
|
DOI | |
发表期刊 | |
ISSN | 1350-7265
|
EISSN | 1573-9759
|
卷号 | 28期号:3 |
摘要 | We establish a Berry-Esseen bound for general multivariate nonlinear statistics by developing a new multivariate type randomized concentration inequality. The bound is the best possible for many known statistics. As applications, Berry-Esseen bounds for M-estimators and averaged stochastic gradient descent algorithms are obtained. |
关键词 | |
相关链接 | [来源记录] |
收录类别 | |
语种 | 英语
|
学校署名 | 第一
|
资助项目 | Shenzhen Outstanding Talents Training Fund[NSFC12031005]
; Hong Kong RGC GRF[14302515,14304917]
; [MOE 2018-T2-076]
|
WOS研究方向 | Mathematics
|
WOS类目 | Statistics & Probability
|
WOS记录号 | WOS:000792361600002
|
出版者 | |
ESI学科分类 | MATHEMATICS
|
来源库 | Web of Science
|
引用统计 |
被引频次[WOS]:4
|
成果类型 | 期刊论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/334728 |
专题 | 理学院_统计与数据科学系 |
作者单位 | 1.Southern Univ Sci & Technol, Dept Stat & Data Sci, Shenzhen, Guangdong, Peoples R China 2.Chinese Univ Hong Kong, Dept Stat, Shatin, Hong Kong, Peoples R China 3.Natl Univ Singapore, Dept Stat & Appl Probabil, Singapore 117546, Singapore |
第一作者单位 | 统计与数据科学系 |
第一作者的第一单位 | 统计与数据科学系 |
推荐引用方式 GB/T 7714 |
Shao, Qi-man,Zhang, Zhuo-song. Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms[J]. BERNOULLI,2022,28(3).
|
APA |
Shao, Qi-man,&Zhang, Zhuo-song.(2022).Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms.BERNOULLI,28(3).
|
MLA |
Shao, Qi-man,et al."Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms".BERNOULLI 28.3(2022).
|
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | 操作 | |
10.3150@21-BEJ1336.p(576KB) | -- | -- | 开放获取 | -- | 浏览 |
|
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论