论文标题
私人预测的权衡
The Trade-Offs of Private Prediction
论文作者
论文摘要
机器学习模型每次揭示预测时泄漏有关培训数据的信息。当培训数据需要保持私密时，这是有问题的。私人预测方法限制了每个预测泄漏有关培训数据的数量。也可以使用经私人培训方法培训的模型来实现私人预测。在私人预测中，私人培训和私人预测方法在隐私，隐私故障概率，培训数据量和推理预算之间都表现出权衡。尽管这些权衡在理论上得到了充分理解，但几乎没有经验研究它们。本文介绍了对私人预测权衡的首次实证研究。我们的研究阐明了哪种方法最适合哪种方法。也许令人惊讶的是，我们发现私人培训方法在广泛的私人预测设置中的表现优于私人预测方法。
Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much information about the training data is leaked by each prediction. Private prediction can also be achieved using models that are trained by private training methods. In private prediction, both private training and private prediction methods exhibit trade-offs between privacy, privacy failure probability, amount of training data, and inference budget. Although these trade-offs are theoretically well-understood, they have hardly been studied empirically. This paper presents the first empirical study into the trade-offs of private prediction. Our study sheds light on which methods are best suited for which learning setting. Perhaps surprisingly, we find private training methods outperform private prediction methods in a wide range of private prediction settings.
