Lower Bounds for Memorization, Privacy and Replicability from Not-So-Strong Data Processing InequalitiesResearch Paper
Top- selection asks an algorithm to look at data records and name of candidate coordinates whose means are nearly the largest. It is a basic subroutine of private and reproducible data analysis: choosing features, hypotheses, or queries before answering them. Two stability requirements are central for it. Differential privacy (Dwork, McSherry,…