# Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms

arXiv: https://arxiv.org/abs/2401.10294 · HTML: https://mlsanity.com/paper/2401.10294/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 17 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [Numerical Composition of Differential Privacy](https://mlsanity.com/paper/2106.02848/) (2021)
- [Privacy Amplification by Iteration](https://mlsanity.com/paper/1808.06651/) (2018)
- [Optimal Accounting of Differential Privacy via Characteristic Function](https://mlsanity.com/paper/2106.08567/) (2021)
- [Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent](https://mlsanity.com/paper/2102.05855/) (2021)
- [Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss](https://mlsanity.com/paper/2205.13710/) (2022)
- [Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions](https://mlsanity.com/paper/2207.04380/) (2022)
- [(Amplified) Banded Matrix Factorization: A unified approach to private training](https://mlsanity.com/paper/2306.08153/) (2023)
- [Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT](https://mlsanity.com/paper/2006.07134/) (2020)

## Built on by (most cited first, 2 of 2)

- [Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning](https://mlsanity.com/paper/2406.14322/) (2024)
- [Differentially Private Relational Learning with Entity-level Privacy Guarantees](https://mlsanity.com/paper/2506.08347/) (2025)

## Abstract (arXiv)

We give a procedure for computing group-level (ε, δ)-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implementation, the DP guarantees computed by this procedure are tight (assuming we release every intermediate iterate).