Research map / Federated learning and privacy / Differential privacy
Locally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use a one-round protocol with dimension reduction and grid-based candidate centers instead of prior LDP approaches | LDP k-means · LDP k-means | additive error dependence on n: n^{1/2 + a} -> \sqrt{n} | Helped |
| Use the four-round LSH-based algorithm with a randomly shifted hierarchy of dyadic cells | LDP k-means · LDP k-means | additive error dependence on k: k \cdot \max \{ \sqrt{d'}, \sqrt{k} \} -> k^{1 + O(1/(2c^2-1))} | Helped |
| Use the four-round LSH-based algorithm rather than prior algorithms with an n^{1/2+a} additive-error factor | LDP k-means · LDP k-means | additive error dependence on n: n^{1/2 + a} -> n^{1/2} | Helped |
Closest papers by meaning
- Online Differentially Private Consistent Clustering (NeurIPS 2026 · similarity 0.90)
- Making Old Things New: A Unified Algorithm for Differentially Private Clustering (ICML 2024 · similarity 0.88)
- Differentially Private Federated $k$-Means Clustering with Server-Side Data (ICML 2025 · similarity 0.88)
- On the Price of Differential Privacy for Hierarchical Clustering (ICLR 2025 · similarity 0.87)
- Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems (ICLR 2025 · similarity 0.86)
- A Differentially Private Clustering Algorithm for Well-Clustered Graphs (ICLR 2024 · 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.