Private Lossless Multiple Release
Joel Daniel Andersson, Lukas Retschmeier, Boel Nelson, Rasmus Pagh
2025Year
Abstract
Koufogiannis et al. (2016) showed a gradual release result for Laplace noise-based differentially private mechanisms: given an ε-DP release, a new release with privacy parameter ε ′ > ε can be computed such that the combined privacy loss of both releases is at most ε ′ and the distribution of the latter is the same as a single release with parameter ε ′ . They also showed gradual release techniques for Gaussian noise, later also explored by Whitehouse et al. (2022) .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on2
Related papers
- Private Hyperparameter Tuning with Ex-Post GuaranteeBadih Ghazi, Pritish Kamath, Alexander Knop, Ravi Kumar et al.NeurIPS 2025 · 4 citations
- Mind the Gap: Mixtures of Gaussians in Approximate Differential PrivacyHuikang Liu, Aras Selvi, Wolfram WiesemannICML 2026
- Adaptive Privacy Composition for Accuracy-first MechanismsRyan M. Rogers, Gennady Samorodnitsky, Zhiwei Steven Wu, Aaditya RamdasNeurIPS 2023 · 6 citations
- Log-Concave and Multivariate Canonical Noise Distributions for Differential PrivacyJordan Awan, Jinshuo DongNeurIPS 2022 · 13 citations
- Private Query Release via the Johnson-Lindenstrauss TransformAleksandar NikolovSODA 2023 · 1 citation
