Optimal Differentially Private Model Training with Public Data

1 code implementation • 26 Jun 2023 • Andrew Lowy, Zeman Li, Tianjian Huang, Meisam Razaviyayn

We show that the optimal error rates can be attained (up to log factors) by either discarding private data and training a public model, or treating public data like it is private and using an optimal DP algorithm.