English(EN) Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT

新算法加速了随机分配的隐私损失核算

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员开发了一种名为多尺度FFT的新算法，该算法显著加速了随机分配采样方案的隐私损失核算。该方法通过将计算复杂度从关于精度参数 alpha 的二次方降低到线性来改进现有技术。新算法还引入了一种更精确的舍入方法，进一步增强了差分私有随机梯度下降 (DP-SGD) 的隐私界限。 AI

影响提高了机器学习训练的隐私保证，可能能够使用更敏感的数据。

排序理由学术论文，详细介绍了新算法及其性能改进。[lever_c_demoted from research: ic=1 ai=1.0]

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: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了新算法及其性能改进。[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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Vitaly Feldman, Moshe Shenfeld · 2026-11-02 05:00

Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT

arXiv:2610.42117v1 Announce Type: new Abstract: In the random allocation sampling scheme each user's data is used in $k$ steps chosen randomly and uniformly from a sequence of $t$ steps. This scheme is known to improve on Poisson sampling in private optimization and in communicat…