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 2201.12018cs.LGcs.CRcs.DS
收藏

差分隐私混合模型中的迁移学习

Transfer Learning In Differential Privacy's Hybrid-Model

Bar-Ilan University(巴伊兰大学)

Refael Kohen, Or Sheffet

摘要:

差分隐私中的混合模型(Avent et al 2017)是本地模型的增强,其中除了N个本地代理之外,我们还得到一个特殊代理的帮助,该代理实际上是一个保管n个额外个人的敏感细节的策展人。在这里,我们研究混合模型中的机器学习问题,其中管理员数据集中的n个个体来自与一般人群(本地代理)不同的分布。我们为这个迁移学习问题给出了一个通用方案-子样本测试-重新加权-,该方案使用迭代子采样和重新加权馆长持有的n个示例,将任何馆长模型DP学习器减少到混合模型学习器,基于Multiplicative-Weights算法的平滑变化(由Bun等人介绍,2020)。我们的计划有一个样本的复杂性,依赖于两个分布之间的卡方分歧。我们给出了最坏情况下的分析界限,我们的私人减少所需的样本的复杂性。为了降低所述样本的复杂性,我们给出了两个具体的例子,我们的样本的复杂性可以大大降低(一个例子是数学分析,而另一个-经验),并提出了几个方向的后续工作。

英文摘要:

The hybrid-model (Avent et al 2017) in Differential Privacy is a an augmentation of the local-model where in addition to N local-agents we are assisted by one special agent who is in fact a curator holding the sensitive details of n additional individuals. Here we study the problem of machine learning in the hybrid-model where the n individuals in the curators dataset are drawn from a different distribution than the one of the general population (the local-agents). We give a general scheme -- Subsample-Test-Reweigh -- for this transfer learning problem, which reduces any curator-model DP-learner to a hybrid-model learner in this setting using iterative subsampling and reweighing of the n examples held by the curator based on a smooth variation of the Multiplicative-Weights algorithm (introduced by Bun et al, 2020). Our scheme has a sample complexity which relies on the chi-squared divergence between the two distributions. We give worst-case analysis bounds on the sample complexity required for our private reduction. Aiming to reduce said sample complexity, we give two specific instances our sample complexity can be drastically reduced (one instance is analyzed mathematically, while the other - empirically) and pose several directions for follow-up work.

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。

↑