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 1906.00930cs.LGstat.ML
收藏

自适应推广的充要稳定性概念

A necessary and sufficient stability notion for adaptive generalization

Katrina Ligett, Moshe Shenfeld

摘要:

我们引入了一个新的概念,计算的稳定性,这在后处理和自适应组合。我们表明,这个概念是必要的和足够的,以确保泛化的适应性,对于任何计算,响应有界灵敏度的线性查询,同时提供准确的数据样本集。稳定性的概念是基于量化的影响,观察计算的输出后的数据样本元素。我们显示了这个稳定的概念和以前研究的概念之间的分离,并观察到所有的差分隐私算法也满足这一概念。

英文摘要:

We introduce a new notion of the stability of computations, which holds under post-processing and adaptive composition. We show that the notion is both necessary and sufficient to ensure generalization in the face of adaptivity, for any computations that respond to bounded-sensitivity linear queries while providing accuracy with respect to the data sample set. The stability notion is based on quantifying the effect of observing a computation's outputs on the posterior over the data sample elements. We show a separation between this stability notion and previously studied notion and observe that all differentially private algorithms also satisfy this notion.

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。

↑