论文标题
部分可观测时空混沌系统的无模型预测
Performances of Symmetric Loss for Private Data from Exponential Mechanism
论文作者
论文摘要
这项研究探讨了通过对称损失在私人数据上学习的鲁棒性。具体来说，我们利用了专用标签上的指数机制（EM）。首先，当EM用于对称损失的私人学习时，我们从理论上重新讨论了EM的属性。然后，我们提出了与不同数据量表和公用事业保证相对应的隐私预算的数值指导。此外，我们在CIFAR-10数据集上进行了实验，以提出对称损失的特征。由于EM是一种更通用的差异隐私（DP）技术，因此它具有强大的潜力，可以将其推广，并使其他DP技术更强大。
This study explores the robustness of learning by symmetric loss on private data. Specifically, we leverage exponential mechanism (EM) on private labels. First, we theoretically re-discussed properties of EM when it is used for private learning with symmetric loss. Then, we propose numerical guidance of privacy budgets corresponding to different data scales and utility guarantees. Further, we conducted experiments on the CIFAR-10 dataset to present the traits of symmetric loss. Since EM is a more generic differential privacy (DP) technique, it being robust has the potential for it to be generalized, and to make other DP techniques more robust.
