We present the first $\varepsilon$-differentially private, computationally efficient algorithm that estimates the means of product distributions over $\{0,1\}^d$ accurately in total-variation distance, whilst attaining the optimal sample complexity to within polylogarithmic factors. The prior work had either solved this problem efficiently and optimally under weaker notions of privacy, or had solved it optimally while having exponential running times.

翻译：我们提出了首个$\varepsilon$-差分隐私、计算高效的算法，该算法能准确地在总变差距离下估计$\{0,1\}^d$上乘积分布的均值，同时样本复杂度在多项式对数因子内达到最优。此前的工作要么在较弱的隐私概念下高效且最优地解决了该问题，要么以指数级运行时间实现了最优解。