English(EN) Differentially Private Synthetic Data via Generalized Moment Matching

新方法使用矩匹配生成差分隐私合成数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种使用广义矩匹配生成差分隐私合成数据的新方法。该技术私有地估计矩，拟合概率测度，然后采样合成记录。该框架适用于各种积分概率度量，包括用于 Wasserstein 距离的 Chebyshev 矩匹配、具有 Matern 和 Laplace 核的最大均值差异以及切片 Wasserstein 距离。结果表明，在固定维度下，生成的合成数据速率接近 minimax 最优。 AI

影响这项研究推进了隐私保护数据合成技术，可能使敏感数据集在 AI 模型训练中得到更广泛的应用。

排序理由该集群包含一篇详细介绍机器学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍机器学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Rundong Ding, Yiyun He, Yizhe Zhu · 2026-10-23 04:00

Differentially Private Synthetic Data via Generalized Moment Matching

arXiv:2610.30196v1 Announce Type: cross Abstract: We study $(\varepsilon,\delta)$-differentially private synthetic data for arbitrary databases of $n$ records in $[-1,1]^d$ under a specified integral probability metric (IPM). We introduce generalized moment matching, which estima…

本文如何被排名

报道来源 [1]

Differentially Private Synthetic Data via Generalized Moment Matching

相关实体

相关话题