AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Multivariate Medians

Kelly Ramsay, Aukosh Jagannath, Shoja'eddin Chenouri

JMLR 2025 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation

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 median instead of mean estimator under 25% contaminationprivate smoothed integrated dual depth median · Contaminated Gaussian, n=10,000, d from 2 to 100empirical RMSEImproved
use mean (coin-press) instead of median without contaminationprivate coin-press mean · Gaussian, n=10,000, d from 2 to 100empirical RMSEImproved
add differential privacy to the smoothed integrated dual depth mediansmoothed integrated dual depth median · Gaussian, n=10,000, d from 2 to 100empirical RMSEHurt
increase smoothing parameter s to at least 10 (ablation)non-private smoothed integrated dual depth median · Gaussian and contaminated Gaussianempirical RMSE: s >= 10Improved
use halfspace depth instead of integrated depthsprivate depth median · Cauchy marginals, discrepancy log(1/alpha(1))discrepancy functionImproved

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