Research map / Federated learning and privacy / Differential privacy
Differential Privacy for Growing Databases
Rachel Cummings, Sara Krehbiel, Kevin A Lai, Uthaipon Tantipongpipat
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Update the public histogram uniformly when new data arrive | PMWG · Growing databases, adaptive linear queries | accuracy bound: C(log(Nn) log(kappa n/beta)/(n epsilon))^(1/3) | Improved |
| Allow delta greater than zero for PMWG | PMWG · Growing databases, adaptive linear queries | accuracy bound: exponent 1/3 -> 1/2 | Improved |
| Use PMWG rather than static PMW to handle database growth | PMW · Growing databases, adaptive linear queries | accuracy: constant loss in accuracy per query relative to the static setting | Improved |
| Run the improving-accuracy scheduler rather than keeping a fixed accuracy guarantee | Static private algorithm on growing databases · Growing databases, linear queries | accuracy as database size grows: alpha_t diminishes inverse polynomially in t; stronger when t >> n^2 | Mixed |
| Use dynamic ERMG instead of static ERM for strongly convex loss | Private ERM · Growing versus static database, strongly convex ERM | excess empirical risk: t^-2 -> t^{-(1-c)} | Mixed |
Closest papers by meaning
- Differentially Private Data Releasing for Smooth Queries (JMLR 2016 · similarity 0.89)
- Relaxed Marginal Consistency for Differentially Private Query Answering (NeurIPS 2021 · similarity 0.88)
- Differential Privacy on Fully Dynamic Streams (NeurIPS 2025 · similarity 0.88)
- Differentially Private Query Release Through Adaptive Projection (ICML 2021 · similarity 0.88)
- On Differential Privacy for Adaptively Solving Search Problems via Sketching (ICML 2025 · similarity 0.87)
- Scalable Private Partition Selection via Adaptive Weighting (ICML 2025 · similarity 0.86)
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.
