AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Extremal Mechanisms for Local Differential Privacy

Peter Kairouz, Sewoong Oh, Pramod Viswanath

JMLR 2016 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 415 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use binary or randomized response mechanism instead of geometric noise mechanismlocal differential privacy mechanism · KL divergence, |X|=6, 100 random instancesnormalized KL divergenceImproved
use randomized response in the high privacy regime instead of the optimal staircase mechanismrandomized response mechanism · KL divergence, |X|=6KL divergence relative to optimal: as bad as 10% of the optimal oneHurt
use binary mechanism in the low privacy regime instead of the optimal staircase mechanismbinary mechanism · KL divergence, |X|=6KL divergence relative to optimal: as bad as 25% of the optimal oneHurt
pick the better of binary and randomized response per instancebinary and randomized response mechanisms · KL divergence, |X| in {3,4,6,12}fraction of optimal KL divergence: at least 70% for |X| = 6 (and 55% for |X| = 12)Improved
use randomized response in the high privacy regime instead of the optimal mechanismrandomized response mechanism · Mutual information, |X|=6mutual information relative to optimal: as bad as 35% of the optimal oneHurt
use binary mechanism in the low privacy regime instead of the optimal mechanismbinary mechanism · Mutual information, |X|=6mutual information relative to optimal: as bad as 40% of the optimal oneHurt
pick the better of binary and randomized response per instancebinary and randomized response mechanisms · Mutual information, |X| in {3,4,6,12}fraction of optimal mutual information: at least 75% for |X| = 6 (and 65% for |X| = 12)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy