论文标题
Dixial Privacy的混合模型中的转移学习
Transfer Learning In Differential Privacy's Hybrid-Model
论文作者
论文摘要
差异隐私的混合模型（Avent等人，2017年）是局部模型的增强，除了n个本地代理外，我们还得到了一位特殊代理商的协助，实际上，他是一名策展人，策划了n个其他人的敏感细节。在这里，我们研究了混合模型中的机器学习问题，其中策展人数据集中的n个个体是从与一般人群（本地代理商）中的分布不同的。我们为这个转移学习问题提供了一个一般方案 - 子样本测试 - 育问题，它在这种情况下将任何策展人模型DP-arearner降低到了混合模型学习者为杂种模型学习者，并使用迭代的子采样和重新重新介绍了策展人基于平稳性变化的策展人的n示例，该示例的平稳变化是由bun and and and and of diff buhorith and and buen and and 2020。我们的方案具有样本复杂性，依赖于两个分布之间的卡方差异。我们对私人减少所需的样本复杂性进行了最差的分析范围。为了降低上述样本复杂性，我们提供了两个特定的实例，我们的样本复杂性可以大大降低（一个实例是数学分析的，而另一个实例在经验上 - 依据），并为后续工作构成了多个方向。
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.
