论文标题
具有自适应k的自适应私有K选择，并应用于多标签PATE
Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE
论文作者
论文摘要
我们为基于私人私有的$ K $选择提供了端到端的基于Renyi DP的框架。与以前需要在$ k $上进行数据独立选择的方法不同，我们建议私下发布$ k $的数据依赖性选择，以使$ k $ th和$ k $ - th和$ k+1）$ st“质量”之间的差距很大。这是通过新闻报道 - 毫无疑问的最大应用实现的。这不仅可以消除一个超参数，而且自适应选择$ k $，还证明了无序集合中顶部$ k $ indices的稳定性，因此我们可以使用提出的测试释放（PTR）的变体释放它们，而不会添加噪音。我们表明，与以前的前$ K $选择算法相比，我们的建设改善了隐私 - 实用性权衡。此外，我们将算法应用于具有大量标签的多标签分类任务中的“教师合奏（PATE）的私人聚合”，并表明它会带来显着的性能提高。
We provide an end-to-end Renyi DP based-framework for differentially private top-$k$ selection. Unlike previous approaches, which require a data-independent choice on $k$, we propose to privately release a data-dependent choice of $k$ such that the gap between $k$-th and the $(k+1)$st "quality" is large. This is achieved by a novel application of the Report-Noisy-Max. Not only does this eliminate one hyperparameter, the adaptive choice of $k$ also certifies the stability of the top-$k$ indices in the unordered set so we can release them using a variant of propose-test-release (PTR) without adding noise. We show that our construction improves the privacy-utility trade-offs compared to the previous top-$k$ selection algorithms theoretically and empirically. Additionally, we apply our algorithm to "Private Aggregation of Teacher Ensembles (PATE)" in multi-label classification tasks with a large number of labels and show that it leads to significant performance gains.
