Estimation Efficiency Under Privacy Constraints
نویسندگان
چکیده
We investigate the problem of estimating a random variable Y ∈ Y under a privacy constraint dictated by another correlated random variable X ∈ X , where estimation efficiency and privacy are assessed in terms of two different loss functions. In the discrete case, we use the Hamming loss function and express the corresponding utility-privacy tradeoff in terms of the privacy-constrained guessing probability h(PXY , ε), the maximum probability Pc(Y |Z) of correctly guessing Y given an auxiliary random variable Z ∈ Z , where the maximization is taken over all PZ|Y ensuring that Pc(X |Z) ≤ ε for a given privacy threshold ε ≥ 0. We prove that h(PXY , ·) is concave and piecewise linear, which allows us to derive its expression in closed for any ε when X and Y are binary. In the non-binary case, we derive h(PXY , ε) in the high utility regime (i.e., for sufficiently large, but nontrivial, values of ε) under the assumption that Z takes values in Y . We also analyze the privacy-constrained guessing probability for two binary vector scenarios. When X and Y are continuous random variables, we use the squared-error loss function and express the corresponding utility-privacy tradeoff in terms of sENSR(PXY , ε), which is the smallest normalized minimum mean squared-error (mmse) incurred in estimating Y from its Gaussian perturbation Z , such that the mmse of f(X) given Z is within ε of the variance of f(X) for any non-constant real-valued function f . We derive tight upper and lower bounds for sENSR when Y is Gaussian. We also obtain a tight lower bound for sENSR(PXY , ε) for general absolutely continuous random variables when ε is sufficiently small.
منابع مشابه
Local Privacy, Data Processing Inequalities, and Statistical Minimax Rates
Working under a model of privacy in which data remains private even from the statistician, we study the tradeoff between privacy guarantees and the utility of the resulting statistical estimators. We prove bounds on information-theoretic quantities, including mutual information and Kullback-Leibler divergence, that depend on the privacy guarantees. When combined with standard minimax techniques...
متن کاملAsymptotically optimal private estimation under mean square loss
We consider the minimax estimation problem of a discrete distribution with support size k under locally differential privacy constraints. A privatization scheme is applied to each raw sample independently, and we need to estimate the distribution of the raw samples from the privatized samples. A positive number ǫ measures the privacy level of a privatization scheme. In our previous work (arXiv:...
متن کاملMinimax Optimal Procedures for Locally Private Estimation
Working under a model of privacy in which data remains private even from the statistician,we study the tradeoff between privacy guarantees and the risk of the resulting statistical estima-tors. We develop private versions of classical information-theoretic bounds, in particular thosedue to Le Cam, Fano, and Assouad. These inequalities allow for a precise characterization ofs...
متن کاملDiscussion on “Minimax Optimal Procedures for Locally Private Estimation”
We congratulate Professors Duchi, Jordan and Wainwright on their path-breaking work in statistical decision theory and privacy. Their extension of classical information-theoretic lower bounds of Le Cam, Fano, and Assouad to local differential privacy can potentially lead to a systematic study of various lower bounds under all kinds of privacy constraints. Their successful treatments of some int...
متن کاملAn Investigation into the Effect of CEO’s Perceptual Biases on Investment Efficiency and Financing Constraints of the Iranian Listed Firms
Efficient market hypothesis predicts that capital markets are beset with cer-tain biases which result from wrong estimation, and negatively influence shareholders’ expectations for higher returns, which in turn affects invest-ment efficiency, financial constraints and corporate performance efficacy in competitive markets, and eventually mitigates firm value. The present study aims at examining ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1707.02409 شماره
صفحات -
تاریخ انتشار 2017