arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09734cs.DScs.CRcs.LG
收藏

单轮局部私有k均值算法

Locally Private k-Means in One Round

Google(谷歌)

Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi

摘要:

我们提供了一个近似算法的k-means聚类在一轮(又名非交互式)的局部模型的差分隐私(DP)。该算法实现了任意接近最佳非私有近似算法的近似比,改进了先前已知的仅保证大(恒定)近似比的算法。此外,这是第一个常数因子近似算法的k-means,只需要一轮的通信在本地DP模型,积极解决一个悬而未决的问题Stemmer(SODA 2020)。我们的算法框架是相当灵活的,我们证明了这一点,它也产生了类似的接近最佳的近似算法(一轮)洗牌DP模型。

英文摘要:

We provide an approximation algorithm for k-means clustering in the one-round (aka non-interactive) local model of differential privacy (DP). This algorithm achieves an approximation ratio arbitrarily close to the best non private approximation algorithm, improving upon previously known algorithms that only guarantee large (constant) approximation ratios. Furthermore, this is the first constant-factor approximation algorithm for k-means that requires only one round of communication in the local DP model, positively resolving an open question of Stemmer (SODA 2020). Our algorithmic framework is quite flexible; we demonstrate this by showing that it also yields a similar near-optimal approximation algorithm in the (one-round) shuffle DP model.

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。

↑