Title :
Privacy: A few definitional aspects and consequences for minimax mean-squared error
Author :
Barber, Rina Foygel ; Duchi, John
Author_Institution :
Dept. of Stat., Univ. of Chicago, Chicago, IL, USA
Abstract :
We explore several definitions of “privacy” in statistical estimation and data analysis. We present and review definitions that attempt to capture what, intuitively, it should mean to limit disclosures from the output of a statistical estimation task, providing minimax upper and lower bounds on mean squared error for estimation problems under several common (and some new) definitions of privacy.
Keywords :
data analysis; data privacy; estimation theory; mean square error methods; minimax techniques; statistical analysis; data analysis; data privacy; minimax mean-squared error; statistical estimation; Computer science; Convergence; Data analysis; Data privacy; Estimation; Privacy; Testing;
Conference_Titel :
Decision and Control (CDC), 2014 IEEE 53rd Annual Conference on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-1-4799-7746-8
DOI :
10.1109/CDC.2014.7039572
