PulseAugur
中
实时 18:45:58
English(EN) Towards Personalized Differentially Private Learning for Decentralized Local Graphs

新的DP-NGD框架提升了隐私保护机器学习的效用和速度 · 跟踪2个来源

作者 PulseAugur 编辑部 · [4 个来源] ·

研究人员开发了DP-NGD，一个新颖的差分隐私自然梯度下降框架，旨在提高隐私保护机器学习的效用。与忽略损失曲率的标准DP-SGD不同，DP-NGD整合了这一信息，以实现更快的收敛速度和更高的准确性。该框架通过解耦曲率估计并采用具有动态钳制的白化空间机制，解决了隐私预算消耗和训练不稳定性等挑战。 AI

影响 这项研究可能带来更高效、更准确的隐私保护机器学习模型，特别是在数据效用至关重要的场景中。

排序理由 该集群包含两篇相同的arXiv预印本，详细介绍了一个用于差分隐私学习的新研究框架。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新的DP-NGD框架提升了隐私保护机器学习的效用和速度 · 跟踪2个来源

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
Research
该集群包含两篇相同的arXiv预印本，详细介绍了一个用于差分隐私学习的新研究框架。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
93 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [4]

  1. arXiv cs.AI TIER_1 English(EN) · Pan Li, Kai Chen, Shuai Chang, Shengzhi Zhang, Peizhuo Lv, Jinwen He ·

    差分隐私自然梯度下降

    arXiv:2607.05866v1 Announce Type: cross Abstract: Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency. Standard first-order DP optimizers such as DP-SGD rely solely on local gradients and ignore…

  2. arXiv cs.LG TIER_1 English(EN) · Jinwen He ·

    差分隐私自然梯度下降

    Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency. Standard first-order DP optimizers such as DP-SGD rely solely on local gradients and ignore the underlying loss curvature. This geometric bli…

  3. arXiv cs.LG TIER_1 English(EN) · Longzhu He, Peng Tang, Chaozhuo Li, Jinhu Fu, Litian Zhang, Li Sun, Philip S. Yu, Sen Su ·

    面向去中心化本地图的个性化差分隐私学习

    arXiv:2607.04777v1 Announce Type: new Abstract: Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data. However, collectin…

  4. arXiv stat.ML TIER_1 English(EN) · Michael Menart, Aleksandar Nikolov ·

    关于带私有预言机的私有优化梯度复杂度

    arXiv:2511.13999v2 Announce Type: replace-cross Abstract: We study the running time, in terms of first order oracle queries, of differentially private empirical/population risk minimization of Lipschitz convex losses. We first consider the setting where the loss is non-smooth and…

相关实体

相关话题