Optimizing Noise Distributions for Differential Privacy
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909643655086080 |
|---|---|
| author | Gilani, Atefeh Gomez, Juan Felipe Asoodeh, Shahab Calmon, Flavio P. Kosut, Oliver Sankar, Lalitha |
| author_facet | Gilani, Atefeh Gomez, Juan Felipe Asoodeh, Shahab Calmon, Flavio P. Kosut, Oliver Sankar, Lalitha |
| contents | We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP, under a cost constraint. Rényi DP has the advantage that by considering different values of the Rényi parameter $α$, we can tailor our optimization for any number of compositions. To solve the optimization problem, we reduce it to a finite-dimensional convex formulation and perform preconditioned gradient descent. The resulting noise distributions are then compared to their Gaussian and Laplace counterparts. Numerical results demonstrate that our optimized distributions are consistently better, with significant improvements in $(\varepsilon, δ)$-DP guarantees in the moderate composition regimes, compared to Gaussian and Laplace distributions with the same variance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14730 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Noise Distributions for Differential Privacy Gilani, Atefeh Gomez, Juan Felipe Asoodeh, Shahab Calmon, Flavio P. Kosut, Oliver Sankar, Lalitha Information Theory We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP, under a cost constraint. Rényi DP has the advantage that by considering different values of the Rényi parameter $α$, we can tailor our optimization for any number of compositions. To solve the optimization problem, we reduce it to a finite-dimensional convex formulation and perform preconditioned gradient descent. The resulting noise distributions are then compared to their Gaussian and Laplace counterparts. Numerical results demonstrate that our optimized distributions are consistently better, with significant improvements in $(\varepsilon, δ)$-DP guarantees in the moderate composition regimes, compared to Gaussian and Laplace distributions with the same variance. |
| title | Optimizing Noise Distributions for Differential Privacy |
| topic | Information Theory |
| url | https://arxiv.org/abs/2504.14730 |