隐私保护下持续估计数据均值与方差，噪声更低更准确。
Continual Release Moment Estimation with Differential Privacy
- 联合敏感性分析+矩阵机制，共享隐私预算
- 二阶矩估计不增加额外隐私开销，精度提升
- 适用于流式数据建模和私有化模型训练
我们提出联合矩估计（JME），一种在持续学习场景下私密估计数据一阶与二阶矩的方法，相比直接应用的朴素方法，能显著降低噪声。JME利用矩阵机制并进行联合敏感性分析，使得二阶矩估计无需额外隐私成本，从而在保障隐私的前提下提升估计精度。我们在两个应用场景中验证了JME的有效性：一是对高斯密度估计所需的运行均值与协方差矩阵进行持续估计；二是使用私有化Adam优化器（DP-Adam）在CIFAR-10上训练模型。
原文摘要 · Abstract (English)
We propose Joint Moment Estimation (JME), a method for continually and privately estimating both the first and second moments of data with reduced noise compared to naive approaches. JME uses the matrix mechanism and a joint sensitivity analysis to allow the second moment estimation with no additional privacy cost, thereby improving accuracy while maintaining privacy. We demonstrate JME's effectiveness in two applications: estimating the running mean and covariance matrix for Gaussian density estimation, and model training with DP-Adam on CIFAR-10.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。