mlsanityData to 14 Oct 2026

Universal Exact Compression of Differentially Private Mechanisms

arXiv 2405.20782 ↗First posted 28 May 2024cs.CR cs.IT math.ITcited by 8

Not on the map. Why?

Abstract (arXiv)

To reduce the communication cost of differential privacy mechanisms, we introduce a novel construction, called Poisson private representation (PPR), designed to compress and simulate any local randomizer while ensuring local differential privacy. Unlike previous simulation-based local differential privacy mechanisms, PPR exactly preserves the joint distribution of the data and the output of the original local randomizer. Hence, the PPR-compressed privacy mechanism retains all desirable statistical properties of the original privacy mechanism such as unbiasedness and Gaussianity. Moreover, PPR achieves a compression size within a logarithmic gap from the theoretical lower bound. Using the PPR, we give a new order-wise trade-off between communication, accuracy, central and local differential privacy for distributed mean estimation. Experiment results on distributed mean estimation show that PPR consistently gives a better trade-off between communication, accuracy and central differential privacy compared to the coordinate subsampled Gaussian mechanism, while also providing local differential privacy.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 82 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

39 of 82 references.

References · 39

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2020Extracting Training Data from Large Language Modelscited by 2,189
  6. 2023Extracting Training Data from Diffusion Modelscited by 732
  7. 2017Renyi Differential Privacycited by 650
  8. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  9. 2014A* Samplingcited by 151
  10. 2016Distributed Mean Estimation with Limited Communicationcited by 136
  11. 2020The Discrete Gaussian for Differential Privacycited by 135
  12. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 130
27 more
  1. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 119
  2. 2020Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shufflingcited by 96
  3. 2022Lossy Compression with Gaussian Diffusioncited by 90
  4. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  5. 2020Universally Quantized Neural Compressioncited by 64
  6. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 58
  7. 2018Generalised Differential Privacy for Text Document Processingcited by 52
  8. 2015Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequalitycited by 50
  9. 2016Differential Privacy as a Mutual Information Constraintcited by 45
  10. 2020Compressing Images by Encoding Their Latent Representations with Relative Entropy Codingcited by 39
  11. 2015Local, Private, Efficient Protocols for Succinct Histogramscited by 36
  12. 2022Optimal Algorithms for Mean Estimation under Local Differential Privacycited by 36
  13. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 35
  14. 2021Algorithms for the Communication of Samplescited by 34
  15. 2021Lossless Compression of Efficient Private Local Randomizerscited by 27
  16. 2014On Communication Cost of Distributed Statistical Estimation and Dimensionalitycited by 24
  17. 2021Optimal Compression of Locally Differentially Private Mechanismscited by 22
  18. 2023Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimationcited by 22
  19. 2017Heavy Hitters and the Structure of Local Privacycited by 20
  20. 2022Privacy-Aware Compression for Federated Data Analysiscited by 17
  21. 2023Compression with Exact Error Distribution for Federated Learningcited by 11
  22. 2021DP-REC: Private & Communication-Efficient Federated Learningcited by 10
  23. 2023Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimationcited by 9
  24. 2023Communication-Efficient Laplace Mechanism for Differential Privacy via Random Quantizationcited by 9
  25. 2023Communication Efficient Private Federated Learning Using Ditheringcited by 9
  26. 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6
  27. 2023Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Scalable Differentially Private Data Compression via Diffusion and Stochastic Codescited by 3
  2. 2025Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learningcited by 2
  3. 2026Accelerating Diffusion Sampling via Speculative Draft Treescited by 2
  4. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysiscited by 1
  5. 2026Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalitiescited by 0
  6. 2026Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacycited by 0
  7. 2026Watermarkable Multi-Draft Speculative Sampling via Poisson Processescited by 0
  8. 2026ExpBoN: Exponential-Noise Best-of-n for Efficient Test-Time LLM Alignmentcited by 0