Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation

UDC 519.21, 517.98, 512.64 In [J.  Cape, et al., Ann. Statist., 47, Article 2405 (2019)], the authors established perturbation bounds for the $\ell_{2 \to \infty}$-norm of singular subspaces and applied this framework to high-dimensional covariance matrix estimation under multivariate normal distrib...

Повний опис

Збережено в:
Бібліографічні деталі
Дата:2026
Автори: Ren, Chunguang, Zhang, Pei, Huang, Shiguo
Формат: Стаття
Мова:Англійська
Опубліковано: Institute of Mathematics, NAS of Ukraine 2026
Онлайн доступ:https://umj.imath.kiev.ua/index.php/umj/article/view/8760
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
Назва журналу:Ukrains’kyi Matematychnyi Zhurnal

Репозитарії

Ukrains’kyi Matematychnyi Zhurnal
_version_ 1866663701030895616
author Ren, Chunguang
Zhang, Pei
Huang, Shiguo
Ren, Chunguang
Zhang, Pei
Huang, Shiguo
author_facet Ren, Chunguang
Zhang, Pei
Huang, Shiguo
Ren, Chunguang
Zhang, Pei
Huang, Shiguo
author_institution_txt_mv [ { "author": "Chunguang Ren", "institution": "School of Mathematics and Information Science, Zhengzhou University of Light Industry, Zhengzhou, China" }, { "author": "Pei Zhang", "institution": "School of Mathematics and Information Science, Zhengzhou University of Light Industry, Zhengzhou, China" }, { "author": "Shiguo Huang", "institution": "School of Mathematics and Information Science, Zhengzhou University of Light Industry, Zhengzhou, China" } ]
author_sort Ren, Chunguang
baseUrl_str https://umj.imath.kiev.ua/index.php/umj/oai
collection OJS
datestamp_date 2026-05-30T12:46:19Z
description UDC 519.21, 517.98, 512.64 In [J.  Cape, et al., Ann. Statist., 47, Article 2405 (2019)], the authors established perturbation bounds for the $\ell_{2 \to \infty}$-norm of singular subspaces and applied this framework to high-dimensional covariance matrix estimation under multivariate normal distributions. We establish perturbation bounds for unitarily invariant norms and apply these bounds to multivariate normal and sub-Gaussian random vectors. Combined with our upper bounds, these results enable us to get the improved estimation of high-dimensional covariance matrices. Finally, we perform simulation experiments demonstrating the  improved scaling behavior as compared to Cape, et al.'s bounds in the presented experiments.
doi_str_mv 10.3842/umzh.v78i5-6.8760
first_indexed 2026-05-30T01:00:42Z
format Article
fulltext
id umjimathkievua-article-8760
institution Ukrains’kyi Matematychnyi Zhurnal
keywords_txt_mv keywords
language English
last_indexed 2026-05-31T01:00:29Z
publishDate 2026
publisher Institute of Mathematics, NAS of Ukraine
record_format ojs
resource_txt_mv
spelling umjimathkievua-article-87602026-05-30T12:46:19Z Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation Ren, Chunguang Zhang, Pei Huang, Shiguo Ren, Chunguang Zhang, Pei Huang, Shiguo Upper bounds, Singular subspace, Unitarily invariant norm, Covariance matrix UDC 519.21, 517.98, 512.64 In [J.  Cape, et al., Ann. Statist., 47, Article 2405 (2019)], the authors established perturbation bounds for the $\ell_{2 \to \infty}$-norm of singular subspaces and applied this framework to high-dimensional covariance matrix estimation under multivariate normal distributions. We establish perturbation bounds for unitarily invariant norms and apply these bounds to multivariate normal and sub-Gaussian random vectors. Combined with our upper bounds, these results enable us to get the improved estimation of high-dimensional covariance matrices. Finally, we perform simulation experiments demonstrating the  improved scaling behavior as compared to Cape, et al.'s bounds in the presented experiments. УДК 519.21, 517.98, 512.64 Верхні межі для сингулярних підпросторів в унітарно-інваріантних нормах та їхнє застосування до оцінювання коваріаційних матриць високої розмірності У роботі Дж. Кейпа та ін. [J.  Cape, et al., Ann. Statist., 47, Article 2405 (2019)] отримано межі збурень для  $\ell_{2 \to \infty}$-норми сингулярних підпросторів і застосовано їх до задачі оцінювання коваріаційних матриць високої розмірності для багатовимірних нормальних розподілів. У цій статті отримано межі збурень для унітарно-інваріантних норм і застосовано їх до багатовимірних нормальних і субгауссових випадкових векторів. Разом із отриманими верхніми межами ці результати дали змогу покращити оцінки для коваріаційних матриць високої розмірності. Насамкінець проведено числові експерименти, які продемонстрували кращу масштабованість результатів  у наведених експериментах порівняно з оцінками Кейпа та ін. Institute of Mathematics, NAS of Ukraine 2026-05-29 Article Article https://umj.imath.kiev.ua/index.php/umj/article/view/8760 10.3842/umzh.v78i5-6.8760 Ukrains’kyi Matematychnyi Zhurnal; Vol. 78 No. 5-6 (2026); 377–378 Український математичний журнал; Том 78 № 5-6 (2026); 377–378 1027-3190 en https://umj.imath.kiev.ua/index.php/umj/article/view/8760/10662 Copyright (c) 2026 Chunguang Ren, Pei Zhang, Shiguo Huang
spellingShingle Ren, Chunguang
Zhang, Pei
Huang, Shiguo
Ren, Chunguang
Zhang, Pei
Huang, Shiguo
Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_alt Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_full Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_fullStr Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_full_unstemmed Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_short Upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
title_sort upper bounds for singular subspaces under unitarily invariant norms with applications to high-dimensional covariance matrix estimation
topic_facet Upper bounds
Singular subspace
Unitarily invariant norm
Covariance matrix
url https://umj.imath.kiev.ua/index.php/umj/article/view/8760
work_keys_str_mv AT renchunguang upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation
AT zhangpei upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation
AT huangshiguo upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation
AT renchunguang upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation
AT zhangpei upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation
AT huangshiguo upperboundsforsingularsubspacesunderunitarilyinvariantnormswithapplicationstohighdimensionalcovariancematrixestimation