Bombari's Question on Sign-Quantized Linear Maps
A dimension-independent subgaussian concentration bound for Gaussian vectors under coordinate-wise nonlinear maps, valid for any bounded function under a well-conditioned covariance, which answers a question of Simone Bombari on sign quantization.
- Result
- Proved
- Status
- Resolved
- AI contribution
- AI-discovered
- Method
- Argument
- Field
- Probability
- Posed by
- Simone Bombari
- Year posed
- —
- Years open
- —
- Solved
- 2026-05-26
- Model
- Gemini 3.5 Flash
- Vendor
- Collaborators
- Guangyi Zou, Roman Vershynin
- Verification
- Unreviewed
- Publication
- Preprint
- Significance
- 10 / 100
- Disclosed cost
- —
- Wikipedia
- No dedicated article
What the AI did
The abstract states the result was discovered by Gemini 3.5 Flash, and the title calls the paper an AI-assisted note. Worth recording that a small fast model, not a frontier reasoning tier, produced it.
Verification
Short arXiv note; not yet peer-reviewed.
Source
arXiv:2605.27563 - On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note