A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences
Harvard University（哈佛大学）；Arizona State University（亚利桑那州立大学）
英文摘要：
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Rényi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and the Rényi variations of differential privacy. We apply our result to the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.
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。
