# Correlated Noise Mechanisms for Differentially Private Learning

arXiv: https://arxiv.org/abs/2506.08201 · HTML: https://mlsanity.com/paper/2506.08201/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2025.

## Built on by (most cited first, 14 of 14)

- [Normalized Square Root: Sharper Matrix Factorization Bounds for Differentially Private Continual Counting](https://mlsanity.com/paper/2509.14334/) (2025)
- [Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation](https://mlsanity.com/paper/2601.21636/) (2026)
- [DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training](https://mlsanity.com/paper/2601.22334/) (2026)
- [JAX-Privacy: A library for differentially private machine learning](https://mlsanity.com/paper/2602.17861/) (2026)
- [Learning Rate Scheduling with Matrix Factorization for Private Training](https://mlsanity.com/paper/2511.17994/) (2025)
- [Correlating Cross-Iteration Noise for DP-SGD using Model Curvature](https://mlsanity.com/paper/2510.05416/) (2025)
- [Cocoon: A System Architecture for Differentially Private Training with Correlated Noises](https://mlsanity.com/paper/2510.07304/) (2025)
- [Limits of Personalizing Differential Privacy Budgets](https://mlsanity.com/paper/2605.13503/) (2026)
- [Beyond Square Roots: A Memory-Efficient Explicit Factorization for Multi-Epoch Private Learning](https://mlsanity.com/paper/2605.18379/) (2026)
- [From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms](https://mlsanity.com/paper/2605.26222/) (2026)
- [Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost](https://mlsanity.com/paper/2605.30476/) (2026)
- [Revisiting the Provable-Auditable Privacy Gap of DP-SGD](https://mlsanity.com/paper/2608.28934/) (2026)
- [The Privacy-Hallucination Tradeoff in Differentially Private Language Models](https://mlsanity.com/paper/2609.00492/) (2026)
- [An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting](https://mlsanity.com/paper/2609.28528/) (2026)

## Abstract (arXiv)

This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine learning models via the core primitive of estimation of weighted prefix sums. While typical DP mechanisms inject independent noise into each step of a stochastic gradient (SGD) learning algorithm in order to protect the privacy of the training data, a growing body of recent research demonstrates that introducing (anti-)correlations in the noise can significantly improve privacy-utility trade-offs by carefully canceling out some of the noise added on earlier steps in subsequent steps. Such correlated noise mechanisms, known variously as matrix mechanisms, factorization mechanisms, and DP-Follow-the-Regularized-Leader (DP-FTRL) when applied to learning algorithms, have also been influential in practice, with industrial deployment at a global scale.