Author

Adya Agrawal

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jun 2026

Let's Ask Gauss: Improved One-Run Privacy Auditing

A DP-auditing framework is developed that leads to tighter privacy lower bounds from a single training run, and is naturally extended to other composition mechanisms that satisfy a classical, triangular-array, or martingale central limit theorem.

Adya Agrawal, Yu Wei, Jaspal Singh et al. · arXiv.org · 0 citations