私有聚类核心集的计算难度
Computational Hardness of Private Coreset
AI总结:
该研究证明了在差分隐私下计算k-均值核心集的计算下界,指出在特定条件下无法在多项式时间内实现该任务。
摘要:
我们研究了在差分隐私(DP)下计算k-均值目标的聚类核心集问题。对于给定的点集,核心集是另一个点集,使得任何候选解的k-均值目标在乘法(1±α)因子(和一些加性因子)下得以保持。我们证明了该问题的第一个计算下界。具体来说,假设存在单向函数,我们证明对于k=3的情况,不存在多项式时间(ε,1/n^{ω(1)})-DP算法能够在ℓ∞度量下计算k-均值的核心集,即使对于某些常数α>0(和某些常数加性因子)。对于欧几里得度量下的k-均值,我们证明了类似的结果,但仅适用于α=Θ(1/d²),其中d是维度。
英文摘要:
We study the problem of differentially private (DP) computation of coreset for the $k$-means objective. For a given input set of points, a coreset is another set of points such that the $k$-means objective for any candidate solution is preserved up to a multiplicative $(1 \pm α)$ factor (and some additive factor). We prove the first computational lower bounds for this problem. Specifically, assuming the existence of one-way functions, we show that no polynomial-time $(ε, 1/n^{ω(1)})$-DP algorithm can compute a coreset for $k$-means in the $\ell_\infty$-metric for some constant $α> 0$ (and some constant additive factor), even for $k=3$. For $k$-means in the Euclidean metric, we show a similar result but only for $α= Θ\left(1/d^2\right)$, where $d$ is the dimension.
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。