Standard techniques for differentially private estimation, such as Laplace or Gaussian noise addition, require guaranteed bounds on the sensitivity of the estimator in question. But such sensitivity bounds are often large or simply unknown. Thus we seek differentially private methods that can be applied to arbitrary black-box functions. A handful of such techniques exist, but all are either inefficient in their use of data or require evaluating the function on exponentially many inputs. In this work we present a scheme that trades off between statistical efficiency (i.e., how much data is needed) and oracle efficiency (i.e., the number of evaluations). We also present lower bounds showing the near-optimality of our scheme.

翻译：差分隐私估计的标准技术（如拉普拉斯或高斯噪声添加）需要保证待估计量的灵敏度界限。然而，此类灵敏度界限往往过大或根本无法获知。因此，我们寻求可应用于任意黑箱函数的差分隐私方法。现有少数此类技术存在数据利用效率低下或需对指数级输入求值的缺陷。本研究提出一种在统计效率（即所需数据量）与预言机效率（即求值次数）之间取得权衡的方案，并给出彰显该方案近最优性的下界。