Giters

opendp / opendp

The core library of differential privacy algorithms powering the OpenDP Project.

Home Page:https://opendp.org

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Explain "evenly amongst three queries"

mccalluc opened this issue · comments

commented

real-world:

Since the privacy loss budget is at most ε = 1, and we are partitioning our budget evenly amongst three queries, then each query will be calibrated to satisfy ε = 1/3.

I may have missed it, but this is the first mention of "three" -- Maybe we want to be explicit about the goal earlier: say that we want a count, a mean, and a variance?