The Restricted Isometry Property of Block Diagonal Matrices Generated by $\varphi$-Sub-Gaussian Variables
Yiming Chen, Guozheng Dai, Kaiti Ding

TL;DR
This paper proves the restricted isometry property for block diagonal matrices with $\, extphi$-sub-Gaussian entries, extending known results and introducing an improved Hanson-Wright inequality of independent interest.
Contribution
It extends the RIP results to $\, extphi$-sub-Gaussian matrices and develops a novel Hanson-Wright deviation inequality.
Findings
RIP holds for block diagonal matrices with $\, extphi$-sub-Gaussian entries
Introduces an improved Hanson-Wright deviation inequality
Extends previous sub-Gaussian RIP results
Abstract
In this paper, we prove the restricted isometry property of block diagonal random matrices with elements from -sub-Gaussian variables, which extends the previously known results for the sub-Gaussian case. A crucial ingredient of our proof is an improved uniform Hanson-Wright deviation inequality, which should be of independent interest.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Mathematical Theories and Applications · Mathematical Inequalities and Applications · Matrix Theory and Algorithms
