Online Learning via Differential Privacy

Online Learning via Differential Privacy
复制标题

通过差异隐私进行在线学习

DOI:
--
复制
发表时间:
2017
期刊:
arXiv.org
影响因子:
--
通讯作者:
Ambuj Tewari
Ambuj Tewari
中科院分区:
--
文献类型:
--
作者:
Jacob D. Abernethy;Chansoo Lee;Audra McMillan;Ambuj Tewari

文献摘要

被引文献

相似文献

我们探讨了在设计和分析在线学习算法中使用差分隐私工具。我们开发了一个简单而强大的分析技术的跟随领导者型算法下的隐私保护扰动。这导致最小最大最优算法k-稀疏在线PCA和最知名的扰动为基础的算法密集在线PCA。我们还表明,在各种在线学习问题中,差分隐私是算法稳定性的核心概念。
We explore the use of tools from differential privacy in the design and analysis of online learning algorithms. We develop a simple and powerful analysis technique for Follow-The-Leader type algorithms under privacy-preserving perturbations. This leads to the minimax optimal algorithm for k-sparse online PCA and the best-known perturbation based algorithm for the dense online PCA. We also show that the differential privacy is the core notion of algorithm stability in various online learning problems.