CSpace  > 应用数学研究所
Matrix optimization based Euclidean embedding with outliers
Zhang, Qian1; Zhao, Xinyuan1; Ding, Chao2
2021-06-01
Source PublicationCOMPUTATIONAL OPTIMIZATION AND APPLICATIONS
ISSN0926-6003
Volume79Issue:2Pages:235-271
AbstractEuclidean embedding from noisy observations containing outlier errors is an important and challenging problem in statistics and machine learning. Many existing methods would struggle with outliers due to a lack of detection ability. In this paper, we propose a matrix optimization based embedding model that can produce reliable embeddings and identify the outliers jointly. We show that the estimators obtained by the proposed method satisfy a non-asymptotic risk bound, implying that the model provides a high accuracy estimator with high probability when the order of the sample size is roughly the degree of freedom up to a logarithmic factor. Moreover, we show that under some mild conditions, the proposed model also can identify the outliers without any prior information with high probability. Finally, numerical experiments demonstrate that the matrix optimization-based model can produce configurations of high quality and successfully identify outliers even for large networks.
KeywordEuclidean embedding Outliers Matrix optimizationg Low-rank matrix Error bound
DOI10.1007/s10589-021-00279-2
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[12071464] ; National Natural Science Foundation of China[11671387] ; National Natural Science Foundation of China[11531014] ; National Natural Science Foundation of China[11688101] ; General Program of Science and Technology of Beijing Municipal Education Commission[KM201810005004] ; Beijing Natural Science Foundation[Z190002]
WOS Research AreaOperations Research & Management Science ; Mathematics
WOS SubjectOperations Research & Management Science ; Mathematics, Applied
WOS IDWOS:000645176600001
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.amss.ac.cn/handle/2S8OKBNM/58594
Collection应用数学研究所
Corresponding AuthorDing, Chao
Affiliation1.Beijing Univ Technol, Coll Appl Sci, Beijing, Peoples R China
2.Chinese Acad Sci, Acad Math & Syst Sci, Inst Appl Math, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Qian,Zhao, Xinyuan,Ding, Chao. Matrix optimization based Euclidean embedding with outliers[J]. COMPUTATIONAL OPTIMIZATION AND APPLICATIONS,2021,79(2):235-271.
APA Zhang, Qian,Zhao, Xinyuan,&Ding, Chao.(2021).Matrix optimization based Euclidean embedding with outliers.COMPUTATIONAL OPTIMIZATION AND APPLICATIONS,79(2),235-271.
MLA Zhang, Qian,et al."Matrix optimization based Euclidean embedding with outliers".COMPUTATIONAL OPTIMIZATION AND APPLICATIONS 79.2(2021):235-271.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Qian]'s Articles
[Zhao, Xinyuan]'s Articles
[Ding, Chao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Qian]'s Articles
[Zhao, Xinyuan]'s Articles
[Ding, Chao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Qian]'s Articles
[Zhao, Xinyuan]'s Articles
[Ding, Chao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.