低秩分解的差分隐私代价
The Price of Differential Privacy for Low-Rank Factorization
摘要:
在本文中,我们研究什么样的价格必须付出释放{ \em差分私有低秩分解矩阵}。我们考虑了接近低秩因式分解在现实世界中应用的各种设置:(i)矩阵更新的方式(逐行或以任意方式),(ii)矩阵是否分布,以及(iii)如何产生输出(在所有更新结束时一次,也称为{ \em单次算法}或连续)。尽管这些设置在没有隐私的情况下得到了很好的研究,但令人惊讶的是,这些设置没有私有算法(除非矩阵逐行更新)。我们提出了第一套差分隐私算法,所有这些设置。当私有矩阵以任意方式更新时,我们的算法承诺差分隐私,相对于两个更强的隐私保证比以前研究的,使用空间和时间{ \em可比}的非私有算法,并实现{ \em最优精度}。为了补充我们的积极成果,我们还证明了我们的算法所需的空间是最佳的对数因子。当数据矩阵分布在多个服务器上时,我们给出了一个非交互的差分隐私算法,其通信代价与维数无关。简单地说,我们给出了算法,产生最优成本。我们还进行了实验,以验证我们所有的算法在实践中表现良好,并优于最好的已知算法,直到现在的大范围的参数。我们给出了实验结果的总近似误差和添加剂的误差为不同的尺寸,$α$和$k$。
英文摘要:
In this paper, we study what price one has to pay to release {\em differentially private low-rank factorization} of a matrix. We consider various settings that are close to the real world applications of low-rank factorization: (i) the manner in which matrices are updated (row by row or in an arbitrary manner), (ii) whether matrices are distributed or not, and (iii) how the output is produced (once at the end of all updates, also known as {\em one-shot algorithms} or continually). Even though these settings are well studied without privacy, surprisingly, there are no private algorithm for these settings (except when a matrix is updated row by row). We present the first set of differentially private algorithms for all these settings. Our algorithms when private matrix is updated in an arbitrary manner promise differential privacy with respect to two stronger privacy guarantees than previously studied, use space and time {\em comparable} to the non-private algorithm, and achieve {\em optimal accuracy}. To complement our positive results, we also prove that the space required by our algorithms is optimal up to logarithmic factors. When data matrices are distributed over multiple servers, we give a non-interactive differentially private algorithm with communication cost independent of dimension. In concise, we give algorithms that incur optimal cost. We also perform experiments to verify that all our algorithms perform well in practice and outperform the best known algorithms until now for large range of parameters. We give experimental results for total approximation error and additive error for varying dimensions, $α$ and $k$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。