Metraipolis › archive › dc_3f632af236de

Differentially Private Synthetic Data from Sliced Chebyshev Moments — arXiv:2610.42081

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42081
License (as archived)
CC0-1.0
Archived
2026-11-03T07:38:28.842Z
SHA-256 of the archived text
d52018368a5953a388315743ab962b19be4f33cbd5aaf9995cb81eb365d23e71
Stable URL of this page
https://metraipolis.com/documento/dc_3f632af236de

How to cite

Differentially Private Synthetic Data from Sliced Chebyshev Moments — arXiv:2610.42081 — arXiv (en), https://arxiv.org/abs/2610.42081 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f632af236de (Metraipolis archive dc_3f632af236de, sha256 d52018368a5953a388315743ab962b19be4f33cbd5aaf9995cb81eb365d23e71)
BibTeX
@misc{dc3f632af236de,
  title = {Differentially Private Synthetic Data from Sliced Chebyshev Moments — arXiv:2610.42081},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42081},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f632af236de; sha256 d52018368a5953a388315743ab962b19be4f33cbd5aaf9995cb81eb365d23e71},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42081. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Research on practical differentially private (DP) synthetic data has largely focused on methods that approximately preserve low-dimensional marginals of a target distribution, and can thus only hope to preserve higher-dimensional, global structure as a lucky by-product. At the same time, existing methods that target global accuracy guarantees pay a price exponential in the data dimension, $d$. In this work, we address this ``curse of dimensionality'' by presenting a new DP synthetic data algorithm, SPLICE, that comes with a compelling global distributional guarantee, even in high-dimensions, and moreover, is practically state-of-the-art. Our algorithm is based on measuring noisy sliced Chebyshev polynomial moments of the target distribution and fitting a distribution to match, a twist on recent polynomial methods for 1-D synthetic data. We prove that, given a dataset of $n$ examples, SPLICE returns a private distribution with Sliced Wasserstein-1 distance $\tilde{O}(1/\sqrt{n})$ from the target, for constant privacy parameters. Notably, this bound is independent of the data dimension, $d$. Along the way, we prove a moment matching result of independent interest: for a distribution on the unit ball, matching the first $O(1/\alpha)$ Chebyshev moments along $\tilde{O}(d/\alpha^2)$ random directions guarantees $\alpha$ Sliced Wasserstein error. Finally, we provide a practical implementation of the algorithm that borrows tools from the tensor decomposition literature and achieves state-of-the-art performance compared to prior DP synthetic data methods on an extensive benchmark.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computers and Society (cs.CY); Data Structures and Algorithms (cs.DS).
Pagina del lavoro: https://arxiv.org/abs/2610.42081 — 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 2026-11-03T07:30:47.627Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).