Privacy Aware Learning
作者： John C Duchi , Michael I Jordan , Martin J Wainwright , None
DOI: 10.1145/2666468
关键词:
摘要: We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from learner. In this local framework, we establish sharp upper and lower bounds on convergence rates of estimation procedures. As consequence, exhibit precise tradeoff between amount preserves utility, as measured by rate, any estimator or learning procedure.
arxiv.org
berkeley.edu
acm.org
stanford.edu参考文章(56)
Robert M. Gray, Entropy and information theory ,(1990)
John Darzentas, Problem complexity and method efficiency in optimization ,(1983)
Yuhong Yang, Andrew Barron, None, Information-theoretic determination of minimax rates of convergence Annals of Statistics. ,vol. 27, pp. 1564- 1599 ,(1999) , 10.1214/AOS/1017939142
Bin Yu, Assouad, Fano, and Le Cam Festschrift for Lucien Le Cam. pp. 423- 435 ,(1997) , 10.1007/978-1-4612-1880-7_29
Janos Korner, Imre Csiszar, Information Theory: Coding Theorems for Discrete Memoryless Systems ,(2014)
Jean-Baptiste Hiriart-Urruty, Claude Lemaréchal, Convex analysis and minimization algorithms ,(1993)
Robert Ralph Phelps, Lectures on Choquet's Theorem ,(1966)
John N. Tsitsiklis, Dimitri P. Bertsekas, Parallel and Distributed Computation: Numerical Methods ,(1989)
Larry Wasserman, Rob Hall, Alessandro Rinaldo, Random Differential Privacy arXiv: Methodology. ,(2011)
Cynthia Dwork, Frank McSherry, Kobbi Nissim, Adam Smith, Calibrating Noise to Sensitivity in Private Data Analysis Theory of Cryptography. ,vol. 3876, pp. 265- 284 ,(2006) , 10.1007/11681878_14