Optimal Differentially Private Sampling of Unbounded Gaussians
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917943988715520 |
|---|---|
| author | Iverson, Valentio Kamath, Gautam Mouzakis, Argyris |
| author_facet | Iverson, Valentio Kamath, Gautam Mouzakis, Argyris |
| contents | We provide the first $\widetilde{\mathcal{O}}\left(d\right)$-sample algorithm for sampling from unbounded Gaussian distributions under the constraint of $\left(\varepsilon, δ\right)$-differential privacy. This is a quadratic improvement over previous results for the same problem, settling an open question of Ghazi, Hu, Kumar, and Manurangsi. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01766 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimal Differentially Private Sampling of Unbounded Gaussians Iverson, Valentio Kamath, Gautam Mouzakis, Argyris Data Structures and Algorithms Cryptography and Security Information Theory Machine Learning We provide the first $\widetilde{\mathcal{O}}\left(d\right)$-sample algorithm for sampling from unbounded Gaussian distributions under the constraint of $\left(\varepsilon, δ\right)$-differential privacy. This is a quadratic improvement over previous results for the same problem, settling an open question of Ghazi, Hu, Kumar, and Manurangsi. |
| title | Optimal Differentially Private Sampling of Unbounded Gaussians |
| topic | Data Structures and Algorithms Cryptography and Security Information Theory Machine Learning |
| url | https://arxiv.org/abs/2503.01766 |