High-Probability Bounds For Heterogeneous Local Differential Privacy

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Aliakbarpour, Maryam, Fallah, Alireza, Roy, Swaha, Stevens, Ria
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915552936591360
author Aliakbarpour, Maryam
Fallah, Alireza
Roy, Swaha
Stevens, Ria
author_facet Aliakbarpour, Maryam
Fallah, Alireza
Roy, Swaha
Stevens, Ria
contents We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper bounds in $\ell_2$-norm that hold with probability at least $1-β$. We complement these results with matching minimax lower bounds, establishing the optimality (up to constants) of our guarantees in the heterogeneous LDP regime. We further study distribution learning in $\ell_\infty$-distance, designing an algorithm with high-probability guarantees under heterogeneous privacy demands. Our techniques offer principled guidance for designing mechanisms in settings with user-specific privacy levels.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11895
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Probability Bounds For Heterogeneous Local Differential Privacy
Aliakbarpour, Maryam
Fallah, Alireza
Roy, Swaha
Stevens, Ria
Machine Learning
Cryptography and Security
Data Structures and Algorithms
We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper bounds in $\ell_2$-norm that hold with probability at least $1-β$. We complement these results with matching minimax lower bounds, establishing the optimality (up to constants) of our guarantees in the heterogeneous LDP regime. We further study distribution learning in $\ell_\infty$-distance, designing an algorithm with high-probability guarantees under heterogeneous privacy demands. Our techniques offer principled guidance for designing mechanisms in settings with user-specific privacy levels.
title High-Probability Bounds For Heterogeneous Local Differential Privacy
topic Machine Learning
Cryptography and Security
Data Structures and Algorithms
url https://arxiv.org/abs/2510.11895