AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differential Privacy for Growing Databases

Rachel Cummings, Sara Krehbiel, Kevin A Lai, Uthaipon Tantipongpipat

NeurIPS 2018 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 5 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
Update the public histogram uniformly when new data arrivePMWG · Growing databases, adaptive linear queriesaccuracy bound: C(log(Nn) log(kappa n/beta)/(n epsilon))^(1/3)Improved
Allow delta greater than zero for PMWGPMWG · Growing databases, adaptive linear queriesaccuracy bound: exponent 1/3 -> 1/2Improved
Use PMWG rather than static PMW to handle database growthPMW · Growing databases, adaptive linear queriesaccuracy: constant loss in accuracy per query relative to the static settingImproved
Run the improving-accuracy scheduler rather than keeping a fixed accuracy guaranteeStatic private algorithm on growing databases · Growing databases, linear queriesaccuracy as database size grows: alpha_t diminishes inverse polynomially in t; stronger when t >> n^2Mixed
Use dynamic ERMG instead of static ERM for strongly convex lossPrivate ERM · Growing versus static database, strongly convex ERMexcess empirical risk: t^-2 -> t^{-(1-c)}Mixed

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