Privacy-Aware Randomized Quantization via Linear Programming
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 1 Jun 2024.
Builds on
22 of 42 references.
References · 22
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
- 2020The Discrete Gaussian for Differential Privacycited by 134
- 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
- 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
- 2023Temporal Dynamic Quantization for Diffusion Modelscited by 81
- 2022Compression of Generative Pre-trained Language Models via Quantizationcited by 79
- 2017Adaptive Quantization for Deep Neural Networkcited by 67
- 2021Robust and Differentially Private Mean Estimationcited by 66
- 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
- 2021Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanismcited by 50
10 more
- 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 40
- 2021Towards Efficient Post-training Quantization of Pre-trained Language Modelscited by 37
- 2018Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithmscited by 20
- 2022Privacy-Aware Compression for Federated Data Analysiscited by 17
- 2020Improving Fairness and Privacy in Selection Problemscited by 16
- 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 16
- 2023Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shiftscited by 14
- 2018Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithmscited by 7
- 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6
- 2019Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithmscited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.