The exact group-sparse recovery for block diagonal matrices with subexponential entries
Probability
2026-03-27 v4
Abstract
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.
Keywords
Cite
@article{arxiv.2506.17965,
title = {The exact group-sparse recovery for block diagonal matrices with subexponential entries},
author = {Guozheng Dai and Tiankun Diao and Hanchao Wang},
journal= {arXiv preprint arXiv:2506.17965},
year = {2026}
}