mlsanityData to 7 Oct 2026

Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy

arXiv 2301.00301 ↗First posted 31 Dec 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

The ''Propose-Test-Release'' (PTR) framework is a classic recipe for designing differentially private (DP) algorithms that are data-adaptive, i.e. those that add less noise when the input dataset is nice. We extend PTR to a more general setting by privately testing data-dependent privacy losses rather than local sensitivity, hence making it applicable beyond the standard noise-adding mechanisms, e.g. to queries with unbounded or undefined sensitivity. We demonstrate the versatility of generalized PTR using private linear regression as a case study. Additionally, we apply our algorithm to solve an open problem from ''Private Aggregation of Teacher Ensembles (PATE)'' -- privately releasing the entire model with a delicate data-dependent analysis.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 31 Dec 2022.

Builds on

15 of 31 references.

References · 15

  1. 2017Renyi Differential Privacycited by 643
  2. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  3. 2018Scalable Private Learning with PATEcited by 266
  4. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 216
  5. 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
  6. 2018Private Selection from Private Candidatescited by 75
  7. 2021Differential privacy and robust statistics in high dimensionscited by 64
  8. 2015Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlocited by 61
  9. 2018Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domaincited by 60
  10. 2022Private Convex Optimization via Exponential Mechanismcited by 47
  11. 2021Privately Publishable Per-instance Privacycited by 12
  12. 2016Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guaranteescited by 10
3 more
  1. 2018An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithmcited by 4
  2. 2022Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learningcited by 4
  3. 2017Per-instance Differential Privacycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 0; 2026: 1.

6 papers.

  1. 2024Differentially Private Next-Token Prediction of Large Language Modelscited by 21
  2. 2023A Randomized Approach for Tight Privacy Accountingcited by 11
  3. 2024Data-adaptive Differentially Private Prompt Synthesis for In-Context Learningcited by 10
  4. 2024Adaptively Private Next-Token Prediction of Large Language Modelscited by 4
  5. 2024Privacy Profiles for Private Selectioncited by 2
  6. 2026DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacycited by 0