arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.07413cs.LG
收藏

动态隐私预算分配提高差分隐私梯度下降的数据效率

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Michigan State University(密歇根州立大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Junyuan Hong, Zhangyang Wang, Jiayu Zhou

摘要:

在许多涉及敏感数据的应用程序中,在保持模型性能的同时保护学习中的隐私变得越来越重要。私有梯度下降(PGD)是一种常用的私有学习框架,它基于差分隐私协议对梯度进行噪声化。最近的研究表明,降低噪声幅度的\emph{dynamic privacy schedules}可以改善在最后迭代的损失,但这种调度的有效性及其与优化算法的联系的理论理解仍然有限。在本文中,我们提供了全面的分析噪声的影响,在动态隐私时间表来回答这些关键问题。首先,我们提出了一个动态的噪声时间表,最大限度地减少PGD的效用上限,并显示如何从每个优化步骤的噪声影响集体影响最终模型的效用。我们的研究还揭示了当使用动量时,动态噪声的影响如何影响变化。我们的经验表明,一般的非凸损失存在的连接,和损失曲率的影响很大。

英文摘要:

Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises gradients based on the Differential Privacy protocol. Recent studies show that \emph{dynamic privacy schedules} of decreasing noise magnitudes can improve loss at the final iteration, and yet theoretical understandings of the effectiveness of such schedules and their connections to optimization algorithms remain limited. In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions. We first present a dynamic noise schedule minimizing the utility upper bound of PGD, and show how the noise influence from each optimization step collectively impacts utility of the final model. Our study also reveals how impacts from dynamic noise influence change when momentum is used. We empirically show the connection exists for general non-convex losses, and the influence is greatly impacted by the loss curvature.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑