How Does Selection Leak Privacy: Revisiting Private Selection and
Improved Results for Hyper-parameter Tuning
How Does Selection Leak Privacy: Revisiting Private Selection and
Improved Results for Hyper-parameter Tuning
We study the problem of guaranteeing Differential Privacy (DP) in hyper-parameter tuning, a crucial process in machine learning involving the selection of the best run from several. Unlike many private algorithms, including the prevalent DP-SGD, the privacy implications of tuning remain insufficiently understood. Recent works propose a generic private solution …