Beyond Worst Case Sensitivity in Private Data Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout (2015, background): “This theorem is a direct consequence of Theorem 6 and Thakurta [2015].”
Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (2020, unknown): “There has been both theoretical [18, 7, 26, 41, 4] and empirical research [40, 33] providing algorithms which can be used for choosing a “near-optimal” value of the clipping norm.”