In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to easy instances of the problem. We construct locally minimax differentially private estimators for one-parameter exponential families and estimating the tail rate of a distribution. In these cases, we show that optimal algorithms for simple hypothesis testing, namely the recent optimal private testers of Canonne et al. (2019), directly inform the design of locally minimax estimation algorithms.
翻译:在这项工作中,我们研究当地迷你最大趋同估计率,但需以美元作为不同的隐私。与最坏的情况(可能是保守的)相比,当地迷你最大最理想的算法必须适应容易出现的问题。我们为单数指数型家庭建造了当地迷你最大私人估计值,并估算了分布的尾数。在这些情况下,我们展示了简单假设测试的最佳算法,即最近最理想的Canonne等人(2019年)的私人测试法,直接为当地迷你最大估计算法的设计提供了参考。