# Privacy-Aware Randomized Quantization via Linear Programming

arXiv: https://arxiv.org/abs/2406.02599 · HTML: https://mlsanity.com/paper/2406.02599/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2102.06387/) (2021)
- [Algorithmic Stability for Adaptive Data Analysis](https://mlsanity.com/paper/1511.02513/) (2015)
- [Temporal Dynamic Quantization for Diffusion Models](https://mlsanity.com/paper/2306.02316/) (2023)
- [Compression of Generative Pre-trained Language Models via Quantization](https://mlsanity.com/paper/2203.10705/) (2022)
- [The Skellam Mechanism for Differentially Private Federated Learning](https://mlsanity.com/paper/2110.04995/) (2021)
- [Adaptive Quantization for Deep Neural Network](https://mlsanity.com/paper/1712.01048/) (2017)
- [Robust and Differentially Private Mean Estimation](https://mlsanity.com/paper/2102.09159/) (2021)
- [Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism](https://mlsanity.com/paper/2111.12981/) (2021)
- [DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning](https://mlsanity.com/paper/2111.00465/) (2021)
- [Towards Efficient Post-training Quantization of Pre-trained Language Models](https://mlsanity.com/paper/2109.15082/) (2021)
- [Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms](https://mlsanity.com/paper/1806.02246/) (2018)
- [Privacy-Aware Compression for Federated Data Analysis](https://mlsanity.com/paper/2203.08134/) (2022)
- [Randomized Quantization is All You Need for Differential Privacy in Federated Learning](https://mlsanity.com/paper/2306.11913/) (2023)
- [Improving Fairness and Privacy in Selection Problems](https://mlsanity.com/paper/2012.03812/) (2020)
- [Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts](https://mlsanity.com/paper/2305.05090/) (2023)
- [Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms](https://mlsanity.com/paper/1810.03197/) (2018)
- [Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design](https://mlsanity.com/paper/2211.03942/) (2022)
- [Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms](https://mlsanity.com/paper/1910.04581/) (2019)

## Built on by (most cited first, 1 of 1)

- [When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs](https://mlsanity.com/paper/2608.25941/) (2026)

## Abstract (arXiv)

Differential privacy mechanisms such as the Gaussian or Laplace mechanism have been widely used in data analytics for preserving individual privacy. However, they are mostly designed for continuous outputs and are unsuitable for scenarios where discrete values are necessary. Although various quantization mechanisms were proposed recently to generate discrete outputs under differential privacy, the outcomes are either biased or have an inferior accuracy-privacy trade-off. In this paper, we propose a family of quantization mechanisms that is unbiased and differentially private. It has a high degree of freedom and we show that some existing mechanisms can be considered as special cases of ours. To find the optimal mechanism, we formulate a linear optimization that can be solved efficiently using linear programming tools. Experiments show that our proposed mechanism can attain a better privacy-accuracy trade-off compared to baselines.