A Preliminaries

Neural Information Processing Systems 

The convention used will be clear depending on the context. Appendix E. A.1 Privacy Preliminaries We define differential privacy and state its closure under post-processing property. When δ = 0, we say that M satisfies ε-differential privacy or pure differential privacy. The DP Assouad's method provides a lower bound for the minimax risk by considering the problem In this work, we make frequent use of exponential families due to their expressive power. We appeal to the following properties of exponential families.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found