The exact group-sparse recovery for block diagonal matrices with subexponential entries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dai, Guozheng, Diao, Tiankun, Wang, Hanchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914423543693312
author Dai, Guozheng
Diao, Tiankun
Wang, Hanchao
author_facet Dai, Guozheng
Diao, Tiankun
Wang, Hanchao
contents We study block-diagonal random matrices with i.i.d. subexponential entries and show that, despite their highly structured form, they already guarantee exact sparse recovery from a nearly optimal number of measurements. When the matrix reduces to a single block, our framework collapses to the classical i.i.d. subexponential ensemble, and our bounds recover the well-known optimal rates previously established for unstructured random matrices.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17965
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The exact group-sparse recovery for block diagonal matrices with subexponential entries
Dai, Guozheng
Diao, Tiankun
Wang, Hanchao
Probability
We study block-diagonal random matrices with i.i.d. subexponential entries and show that, despite their highly structured form, they already guarantee exact sparse recovery from a nearly optimal number of measurements. When the matrix reduces to a single block, our framework collapses to the classical i.i.d. subexponential ensemble, and our bounds recover the well-known optimal rates previously established for unstructured random matrices.
title The exact group-sparse recovery for block diagonal matrices with subexponential entries
topic Probability
url https://arxiv.org/abs/2506.17965