Preprint
Oct 2026
Local Sensitivity in Exponential Selection: Failure Modes and Valid Calibrations
Selection is a task that chooses one element from a finite public candidate range to maximize a data-dependent score. In differential privacy (DP), the exponential mechanism (EM) samples a candidate at a temperature calibrated to the global sensitivity. In this paper, we study when dataset-dependent sensitivity can saf...
Dung Nguyen, Anil Vullikanti
· 0 citations