Metraipolis › archive › dc_f756bb92c79a
Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy — arXiv:2610.21033
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21033
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:19:24.754Z
- SHA-256 of the archived text
10eec06dfdc01884ef42b2ce3134be8526a2622378198d5073d010a749d1afe8- Stable URL of this page
https://metraipolis.com/documento/dc_f756bb92c79a
How to cite
Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy — arXiv:2610.21033 — arXiv (en), https://arxiv.org/abs/2610.21033 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f756bb92c79a (Metraipolis archive dc_f756bb92c79a, sha256 10eec06dfdc01884ef42b2ce3134be8526a2622378198d5073d010a749d1afe8)
BibTeX
@misc{dcf756bb92c79a,
title = {Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy — arXiv:2610.21033},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21033},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f756bb92c79a; sha256 10eec06dfdc01884ef42b2ce3134be8526a2622378198d5073d010a749d1afe8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21033. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be approximated by piece-wise polynomials. This gives the first sample-efficient LDP learners for several distribution classes, including mixtures of log-concave distributions, such as Gaussian mixture models (GMMs). These learners also provide agnostic guarantees and are computationally efficient. We also prove a lower bound for learning GMMs under LDP, improving on the standard pure-DP packing lower bounds of Bun et al. [BKSW19]. To obtain our general learning framework, we develop an efficient non-interactive LDP algorithm for synthetic data generation over large domains, which may be of independent interest. We then use it together with a deterministic adaptation of the non-private piecewise polynomial learner of Acharya et al. [ADLS17]. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Cryptography and Security (cs.CR); Data Structures and Algorithms (cs.DS); Information Theory (cs.IT); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.21033 — 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 2026-10-16T08:47:32.620Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).