English(EN) Federated and differentially private estimation of KL divergence

新方法在联邦学习中以差分隐私估计KL散度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-24 04:00

研究人员开发了FedPriKL，一种在联邦学习环境中估计Kullback–Leibler散度并确保差分隐私的新方法。该方法旨在解决由于隐私问题或通信成本而直接共享分布信息的挑战。FedPriKL被设计为具有低敏感性和方差的无偏估计，在差分隐私下提供强大的效用。实证研究表明，它达到了与非隐私方法相当的准确性，并且优于基线隐私保护变体。 AI

影响增强了分布式机器学习应用的隐私保护技术。

排序理由该项目是一篇研究论文，详细介绍了一种使用差分隐私估计KL散度的新颖方法。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一种使用差分隐私估计KL散度的新颖方法。[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, safety; 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: 49 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Sayan Biswas, Graham Cormode, Carsten Maple, Mary Scott · 2026-08-24 04:00

联邦化和差分隐私的KL散度估计

arXiv:2411.16478v3 Announce Type: replace Abstract: Measuring distribution drifts is a key task in managing distributed, sensitive data, as it underpins a wide range of federated learning and analytics applications. In many practical settings, however, directly sharing such infor…

本文如何被排名

报道来源 [1]

联邦化和差分隐私的KL散度估计

相关实体

相关话题