Random matrices acting on sets: Independent columns
Probability
2025-09-05 v2
Abstract
We study random matrices with independent subgaussian columns. Assuming each column has a fixed Euclidean norm, we establish conditions under which such matrices act as near-isometries when restricted to a given subset of their domain. We show that, with high probability, the maximum distortion caused by such a matrix is proportional to the Gaussian complexity of the subset, scaled by the subgaussian norm of the matrix columns. This linear dependence on the subgaussian norm is a new phenomenon, as random matrices with independent rows or independent entries typically exhibit superlinear dependence. As a consequence, normalizing the columns of random sparse matrices leads to stronger embedding guarantees.
Cite
@article{arxiv.2502.16827,
title = {Random matrices acting on sets: Independent columns},
author = {Yaniv Plan and Roman Vershynin},
journal= {arXiv preprint arXiv:2502.16827},
year = {2025}
}