arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1304.3754cs.DS
收藏

在小型数据库上更快地私有释放边缘数据

Faster Private Release of Marginals on Small Databases

Karthekeyan Chandrasekaran, Justin Thaler, Jonathan Ullman, Andrew Wan

摘要:

我们研究的问题回答\emph{$k$-way marginal}查询数据库$D \in (\{0,1\}^d)^n$,同时保持差分隐私。$k$方式边际查询的答案是数据库记录$x \in \{0,1\}^d$中具有给定值的部分,这些记录在给定的一组最多$k$列中的每一列中具有给定值。边缘查询使得数据集上的丰富的统计分析,并设计有效的算法,私下回答边缘查询已被确定为一个重要的公开问题,在私人数据分析。对于任何$k$,我们给出了一个差分私人在线算法,运行时间$$ \min{\exp(d^{1-Ω(1/\sqrt{k})}), \exp(d / \log^{.99} d)\} $$每个查询和回答任何(可能superpolynomially长和自适应选择)序列的$k$ -路边际查询错误最多$\pm .01$在每个查询,提供$n \gtrsim d^{.51} $。据我们所知,这是第一个算法能够私下回答边际查询与非平凡的最坏情况下的准确性保证数据库的大小$\poly(d, k)$的时间$\exp(o(d))$。我们的算法是私有乘法权重算法(Hardt和Rothblum,FOCS '10)的变体,但使用不同的低权重数据库表示。我们推导出我们的低权重表示使用近似的或功能的低次多项式系数有界$L_1$ -范数。我们还证明了一个强大的限制,我们的方法是独立的近似理论的兴趣。具体来说,我们表明,对于任何$k = o(\log d)$,任何多项式的系数$L_1$ -范数$poly(d)$逐点近似的$d$ -变量或功能的所有输入的汉明重量最多$k$必须有程度$d^{1-O(1/\sqrt{k})}$。

英文摘要:

We study the problem of answering \emph{$k$-way marginal} queries on a database $D \in (\{0,1\}^d)^n$, while preserving differential privacy. The answer to a $k$-way marginal query is the fraction of the database's records $x \in \{0,1\}^d$ with a given value in each of a given set of up to $k$ columns. Marginal queries enable a rich class of statistical analyses on a dataset, and designing efficient algorithms for privately answering marginal queries has been identified as an important open problem in private data analysis. For any $k$, we give a differentially private online algorithm that runs in time $$ \min{\exp(d^{1-Ω(1/\sqrt{k})}), \exp(d / \log^{.99} d)\} $$ per query and answers any (possibly superpolynomially long and adaptively chosen) sequence of $k$-way marginal queries up to error at most $\pm .01$ on every query, provided $n \gtrsim d^{.51} $. To the best of our knowledge, this is the first algorithm capable of privately answering marginal queries with a non-trivial worst-case accuracy guarantee on a database of size $\poly(d, k)$ in time $\exp(o(d))$. Our algorithms are a variant of the private multiplicative weights algorithm (Hardt and Rothblum, FOCS '10), but using a different low-weight representation of the database. We derive our low-weight representation using approximations to the OR function by low-degree polynomials with coefficients of bounded $L_1$-norm. We also prove a strong limitation on our approach that is of independent approximation-theoretic interest. Specifically, we show that for any $k = o(\log d)$, any polynomial with coefficients of $L_1$-norm $poly(d)$ that pointwise approximates the $d$-variate OR function on all inputs of Hamming weight at most $k$ must have degree $d^{1-O(1/\sqrt{k})}$.

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。

↑