Lower Bounds for Differentially Private ERM: Unconstrained and Non-Euclidean

28 May 2021  ·  Daogao Liu, Zhou Lu ·

We consider the lower bounds of differentially private empirical risk minimization (DP-ERM) for convex functions in constrained/unconstrained cases with respect to the general $\ell_p$ norm beyond the $\ell_2$ norm considered by most of the previous works. We provide a simple black-box reduction approach which can generalize lower bounds in constrained case to unconstrained case. For $(\epsilon,\delta)$-DP, we achieve $\Omega(\frac{\sqrt{d \log(1/\delta)}}{\epsilon n})$ lower bounds for both constrained and unconstrained cases and any $\ell_p$ geometry where $p\geq 1$ by introducing a novel biased mean property for fingerprinting codes, where $n$ is the size of the data-set and $d$ is the dimension.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here