AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

A Differentially Private Linear-Time fPTAS for the Minimum Enclosing Ball Problem

Bar Mahpud, Or Sheffet

NeurIPS 2022 · Federated learning and privacy › Differential privacy · approach: Differentially private clustering · 0 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
Replace exact uncovered-point means with noisy updates, a smaller update rate, and repeated runs (ablation)MMEB · MEB, when r\geq r_{opt}probability of returning a center covering all points within (1+\gamma)r: w.p. \geq 1-\betaImproved
Use an approximate mean with arbitrary noise bounded by \frac{\gamma r}{16} and update rate \frac{\gamma^2}{8} (ablation)MMEB · MEB, r_{opt}\leq r\leq 4r_{opt}center distance to the optimal center: \|[?]Improved
Increase the approximation parameter \gammaDP-MEB experiments · Synthetic datasets and Bar Crawliterations until convergenceImproved
Vary privacy parameter \rhoDP-MEB experiments · Synthetic datasets and Bar Crawlhalting timeNo clear effect
Use data whose mean and 1-center are far apartDP-MEB · Conditional Gaussian and Product Distributioniterations until convergenceNo clear effect
Run the algorithm on Bar Crawl with \gamma=0.1DP-MEB · Bar CrawlconvergenceHurt

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