On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914606577876992 |
|---|---|
| author | Zou, Guangyi Vershynin, Roman |
| author_facet | Zou, Guangyi Vershynin, Roman |
| contents | 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 $Y = \text{sgn}(Wx)$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27563 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note Zou, Guangyi Vershynin, Roman Probability Artificial Intelligence Machine Learning 60G15 (Primary), 60B20, 60E15 (Secondary) 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 $Y = \text{sgn}(Wx)$. |
| title | On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note |
| topic | Probability Artificial Intelligence Machine Learning 60G15 (Primary), 60B20, 60E15 (Secondary) |
| url | https://arxiv.org/abs/2605.27563 |