Metraipolis › archive › dc_1e460cbc2fbf
Geometry-Adaptive Mechanisms for Private Synthetic Data — arXiv:2609.33363
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33363
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:35:03.330Z
- SHA-256 of the archived text
d7f27c0dd89c23af92f9b4e965a942be8c4a6f4bd3c64cf7e48cda8caded2a56- Stable URL of this page
https://metraipolis.com/documento/dc_1e460cbc2fbf
How to cite
Geometry-Adaptive Mechanisms for Private Synthetic Data — arXiv:2609.33363 — arXiv (en), https://arxiv.org/abs/2609.33363 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1e460cbc2fbf (Metraipolis archive dc_1e460cbc2fbf, sha256 d7f27c0dd89c23af92f9b4e965a942be8c4a6f4bd3c64cf7e48cda8caded2a56)
BibTeX
@misc{dc1e460cbc2fbf,
title = {Geometry-Adaptive Mechanisms for Private Synthetic Data — arXiv:2609.33363},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33363},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1e460cbc2fbf; sha256 d7f27c0dd89c23af92f9b4e965a942be8c4a6f4bd3c64cf7e48cda8caded2a56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33363. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating differentially private synthetic data with meaningful Wasserstein utility guarantees is challenging in high dimensions. For datasets of size \(n\) on $[0,1]^d$ with $d\ge2$, existing pure \(\varepsilon\)-differentially private mechanisms achieve expected $1$-Wasserstein error of order $(\varepsilon n)^{-1/d}$, reflecting the curse of dimensionality. While this rate is optimal in the worst case, it can be overly pessimistic when the data are supported on a lower-dimensional set. We formalize this through a multiscale packing-growth dimension $k$, which captures the geometric complexity of the support via the growth of packing numbers across scales. We propose \emph{Adaptive Pruned-PMM}, a pure $\varepsilon$-differentially private mechanism that combines private depth selection with our pruned variant of the Private Measure Mechanism (PMM) of He et al.\ (2023). The mechanism supports deeper, geometry-adapted hierarchies with expected running time $O\!\left(d(n+d)\log(\varepsilon n)\right)$, which is near-linear in $n$ for fixed dimension and privacy budget. Under an external multiscale packing-growth condition with dimension $k$, we show that, for fixed positive privacy budgets and fixed geometry, the expected $1$-Wasserstein error is of order $(\varepsilon n)^{-1/k}$ for $k>1$ as $n$ grows. We also prove a lower bound under a corresponding internal packing-growth condition, showing that the exponent $1/k$ is sharp within this framework.
Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CR).
Categorie arXiv: Data Structures and Algorithms (cs.DS) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33363 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:13:03.771Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).