English

On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note

Probability 2026-05-28 v1 Artificial Intelligence Machine Learning

Abstract

This short note presents a dimension-independent subgaussian concentration bound for Gaussian vectors under coordinate-wise nonlinear mappings. Discovered by Gemini 3.5 Flash, this result applies to any bounded function under a well-conditioned covariance. We apply this tool to answer a question of Simone Bombari on sign-quantized linear maps Y=sgn(Wx)Y = \text{sgn}(Wx).

Keywords

Cite

@article{arxiv.2605.27563,
  title  = {On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note},
  author = {Guangyi Zou and Roman Vershynin},
  journal= {arXiv preprint arXiv:2605.27563},
  year   = {2026}
}

Comments

4 pages

R2 v1 2026-07-22T07:35:30.132Z