Revisiting differentially private linear regression: optimal and adaptive prediction estimation in unbounded domain
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE(2018)
摘要
We revisit the problem of linear regression under a differential privacy constraint. By consolidating existing pieces in the literature, we clarify the correct dependence of the feature, label and coefficient domains in the optimization error and estimation error, hence revealing the delicate price of differential privacy in statistical estimation and statistical learning. Moreover, we propose simple modifications of two existing DP algorithms: (a) posterior sampling, (b) sufficient statistics perturbation, and show that they can be upgraded into **adaptive** algorithms that are able to exploit data-dependent quantities and behave nearly optimally **for every instance**. Extensive experiments are conducted on both simulated data and real data, which conclude that both AdaOPS and AdaSSP outperform the existing techniques on nearly all 36 data sets that we test on.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络