Research map / Federated learning and privacy / Differential privacy
Differentially Private Database Release via Kernel Mean Embeddings
Matej Balog, Ilya Tolstikhin, Bernhard Schölkopf
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 |
|---|---|---|---|
| Privately reweight public points using the larger private dataset instead of using uniform weights | Synthetic Data Subspace · Synthetic data, publishable subset | KME estimation accuracy | Improved |
| Optimize synthetic data point locations as well as their weights | Random Features RKHS · Synthetic data, D = 5 | RKHS error | Improved |
Closest papers by meaning
- Minimax Optimal Estimation of Approximate Differential Privacy on Neighboring Databases (NeurIPS 2019 · similarity 0.89)
- Bayesian Pseudo Posterior Mechanism under Asymptotic Differential Privacy (JMLR 2022 · similarity 0.88)
- Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features (NeurIPS 2024 · similarity 0.87)
- Privacy Amplification Persists under Unlimited Synthetic Data Release (NeurIPS 2026 · similarity 0.87)
- Learning from End User Data with Shuffled Differential Privacy over Kernel Densities (ICLR 2025 · similarity 0.87)
- A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy (NeurIPS 2024 · similarity 0.87)
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.
