Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.10294 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913263852191744 |
|---|---|
| author | Ganesh, Arun |
| author_facet | Ganesh, Arun |
| contents | We give a procedure for computing group-level $(ε, δ)$-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implementation, the DP guarantees computed by this procedure are tight (assuming we release every intermediate iterate). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10294 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms Ganesh, Arun Cryptography and Security Machine Learning We give a procedure for computing group-level $(ε, δ)$-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implementation, the DP guarantees computed by this procedure are tight (assuming we release every intermediate iterate). |
| title | Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2401.10294 |