期刊
JOURNAL OF THE ACM
卷 61, 期 6, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/2666468
关键词
Algorithms; Theory; Security; Differential privacy; lower bounds; machine learning; minimax convergence rates; saddle points
类别
资金
- ONR MURI [N00014-11-1-0688]
- U.S. Army Research Laboratory
- U.S. Army Research Office [W911NF-11-1-0391]
- National Defense Science and Engineering Graduate Fellowship Program (NDSEG)
- Facebook Ph.D. fellowship
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff between the amount of privacy the data preserves and the utility, as -measured by convergence rate, of any statistical estimator or learning procedure. Categories and Subject Descriptors: G.1.6 [Numerical Analysis]: Optimization Convex programming; gradient methods; G.8 [Probability and Statistics]: Nonparametric statistics; H.1.1 [Models and Principles]: Systems and information Theory Information theory; 1.2.6 [Artificial Intelligence]: Learning-Parameter learning; K.4.1 [Computers and Society]: Public Policy issue - Privacy
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据