Factorization by extremal privacy mechanisms: new insights into efficiency
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912508707602432 |
|---|---|
| author | Amorino, Chiara Gloter, Arnaud |
| author_facet | Amorino, Chiara Gloter, Arnaud |
| contents | We study the problem of efficiency under $α$ local differential privacy ($α$ LDP) in both discrete and continuous settings. Building on a factorization lemma, which shows that any privacy mechanism can be decomposed into an extremal mechanism followed by additional randomization, we reduce the Fisher information maximization problem to a search over extremal mechanisms. The representation of extremal mechanisms requires working in infinite dimensional spaces and invokes advanced tools from convex and functional analysis, such as Choquet's theorem. Our analysis establishes matching upper and lower bounds on the Fisher information in the high privacy regime ($α\to 0$), and proves that the maximization problem always admits a solution for any $α$. As a concrete application, we consider the problem of estimating the parameter of a uniform distribution on $[0, θ]$ under $α$ LDP. Guided by our theoretical findings, we design an extremal mechanism that yields a consistent and asymptotically efficient estimator in high privacy regime. Numerical experiments confirm our theoretical results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Factorization by extremal privacy mechanisms: new insights into efficiency Amorino, Chiara Gloter, Arnaud Statistics Theory Probability 2020 subject classifications: Primary 62F12, 68P27, secondary 62B15, 46A55 We study the problem of efficiency under $α$ local differential privacy ($α$ LDP) in both discrete and continuous settings. Building on a factorization lemma, which shows that any privacy mechanism can be decomposed into an extremal mechanism followed by additional randomization, we reduce the Fisher information maximization problem to a search over extremal mechanisms. The representation of extremal mechanisms requires working in infinite dimensional spaces and invokes advanced tools from convex and functional analysis, such as Choquet's theorem. Our analysis establishes matching upper and lower bounds on the Fisher information in the high privacy regime ($α\to 0$), and proves that the maximization problem always admits a solution for any $α$. As a concrete application, we consider the problem of estimating the parameter of a uniform distribution on $[0, θ]$ under $α$ LDP. Guided by our theoretical findings, we design an extremal mechanism that yields a consistent and asymptotically efficient estimator in high privacy regime. Numerical experiments confirm our theoretical results. |
| title | Factorization by extremal privacy mechanisms: new insights into efficiency |
| topic | Statistics Theory Probability 2020 subject classifications: Primary 62F12, 68P27, secondary 62B15, 46A55 |
| url | https://arxiv.org/abs/2507.21769 |