Newest papers

Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy

Gautam Kamath, Mahbod Majid, Ankur Moitra, Argyris Mouzakis, Jonathan Ullman · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31612 · open-access PDF

Russian

Мы изучаем изучение дискретного распределения при дифференциальной конфиденциальности на уровне человека в пакете. Учитывая пользователей $n$, каждый из которых вносит $m$ i.i.d. образцы из неизвестного распределения $μ$ над $[k]$, мы ищем оценку $μ$ с ошибкой общей вариации $α$. Мы даем алгоритмы полиномического времени как при чистом, так и при приблизительном дифференциальном конфиденциальности. Под чистым $(\varepsilon,0)$-DP мы сообщаем $n = \widetilde O(k/(α^2 m)+k/(α\sqrt{m}\varepsilon)+k/varepsilon)$, первая полиноми

Machine translation (Meta M2M100); the English original follows.

Abstract

We study learning a discrete distribution under person-level differential privacy in the batched setting. Given $n$ users, each contributing $m$ i.i.d. samples from an unknown distribution $μ$ over $[k]$, we seek an estimate of $μ$ with total-variation error $α$. We give polynomial-time algorithms under both pure and approximate differential privacy. Under pure $(\varepsilon,0)$-DP, we achieve $n = \widetilde O(k/(α^2 m)+k/(α\sqrt{m}\varepsilon)+k/\varepsilon)$, the first polynomial-time pure-DP guarantee matching the information-theoretic optimum up to logarithmic factors. Under approximate $

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31612, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange