mlsanityData to 7 Oct 2026

Leveraging Public Data for Practical Private Query Release

arXiv 2102.08598 ↗First posted 17 Feb 2021cs.LG cs.CR cs.DScited by 39

Not on the map. Why?

Abstract (arXiv)

In many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained underexplored, despite such priors commonly being available in the form of public datasets, such as previous US Census releases. With the goal of releasing statistics about a private dataset, we present PMW^Pub, which -- unlike existing baselines -- leverages public data drawn from a related distribution as prior information. We provide a theoretical analysis and an empirical evaluation on the American Community Survey (ACS) and ADULT datasets, which shows that our method outperforms state-of-the-art methods. Furthermore, PMW^Pub scales well to high-dimensional data domains, where running many existing methods would be computationally infeasible.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 17 Feb 2021.

Builds on

18 of 39 references.

References · 18

  1. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  2. 2018Scalable Private Learning with PATEcited by 266
  3. 2016Concentrated Differential Privacycited by 139
  4. 2020The Discrete Gaussian for Differential Privacycited by 134
  5. 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
  6. 2013Fingerprinting Codes and the Price of Approximate Differential Privacycited by 81
  7. 2014Private Learning and Sanitization: Pure vs. Approximate Differential Privacycited by 62
  8. 2018Privacy-preserving Predictioncited by 48
  9. 2020New Oracle-Efficient Algorithms for Private Synthetic Data Releasecited by 43
  10. 2019Limits of Private Learning with Access to Public Datacited by 38
  11. 2018Optimizing error of high-dimensional statistical queries under differential privacycited by 29
  12. 2020Private Query Release Assisted by Public Datacited by 27
6 more
  1. 2014Dual Query: Practical Private Query Release for High Dimensional Datacited by 26
  2. 2020Permute-and-Flip: A new mechanism for differentially private selectioncited by 22
  3. 2020Private Post-GAN Boostingcited by 20
  4. 2020Learning from Mixtures of Private and Public Populationscited by 19
  5. 2019Privately Answering Classification Queries in the Agnostic PAC Modelcited by 18
  6. 2014Private Multiplicative Weights Beyond Linear Queriescited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 11; 2024: 7; 2025: 9; 2026: 1.

39 papers.

Sort:

By area:

  1. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  2. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 58
  3. 2021Public Data-Assisted Mirror Descent for Private Model Trainingcited by 49
  4. 2022When Does Differentially Private Learning Not Suffer in High Dimensions?cited by 48
  5. 2023Why Is Public Pretraining Necessary for Private Model Training?cited by 36
  6. 2022Private Estimation with Public Datacited by 31
  7. 2023Selective Pre-training for Private Fine-tuningcited by 22
  8. 2023Generating Private Synthetic Data with Genetic Algorithmscited by 18
  9. 2023Private Distribution Learning with Public Data: The View from Sample Compressioncited by 14
  10. 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacycited by 10
  11. 2023Post-processing Private Synthetic Data for Improving Utility on Selected Measurescited by 9
  12. 2024Privacy-preserving data release leveraging optimal transport and particle gradient descentcited by 8
27 more
  1. 2024Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Datacited by 8
  2. 2024Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learningcited by 8
  3. 2025Synthetic Tabular Data: Methods, Attacks and Defensescited by 8
  4. 2023Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Freecited by 6
  5. 2023Mean Estimation Under Heterogeneous Privacy Demandscited by 6
  6. 2021Relaxed Marginal Consistency for Differentially Private Query Answeringcited by 5
  7. 2022Learning-Augmented Private Algorithms for Multiple Quantile Releasecited by 5
  8. 2023On the Benefits of Public Representations for Private Transfer Learning under Distribution Shiftcited by 5
  9. 2024Oracle-Efficient Differentially Private Learning with Public Datacited by 5
  10. 2025Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?cited by 5
  11. 2021Mitigating Statistical Bias within Differentially Private Synthetic Datacited by 4
  12. 2023Can Membership Inferencing be Refuted?cited by 4
  13. 2022Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Samplingcited by 3
  14. 2024Credit Attribution and Stable Compressioncited by 3
  15. 2022Private Synthetic Data with Hierarchical Structurecited by 2
  16. 2022Answering Private Linear Queries Adaptively using the Common Mechanismcited by 2
  17. 2023ResidualPlanner+: a scalable matrix mechanism for marginals and beyondcited by 2
  18. 2023Differentially Private Heavy Hitter Detection using Federated Analyticscited by 2
  19. 2024Differentially Private Synthetic Data Generation for Relational Databasescited by 2
  20. 2024Private Estimation when Data and Privacy Demands are Correlatedcited by 2
  21. 2025RAPID: Retrieval Augmented Training of Differentially Private Diffusion Modelscited by 2
  22. 2025Leveraging Vertical Public-Private Split for Improved Synthetic Data Generationcited by 2
  23. 2025Managing Correlations in Data and Privacy Demandcited by 2
  24. 2025Lower Bounds for Public-Private Learning under Distribution Shiftcited by 0
  25. 2025Enhancing Differentially Private Linear Regression via Public Second-Momentcited by 0
  26. 2025DPSR: Differentially Private Sparse Reconstruction via Multi-Stage Denoising for Recommender Systemscited by 0
  27. 2026Differentially Private Truncation of Unbounded Data via Public Second Momentscited by 0