Research map / Federated learning and privacy / Differential privacy
Differentially Private Topological Data Analysis
Taegyu Kang, Sehwan Kim, Jinwon Sohn, Jordan Awan
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 |
|---|---|---|---|
| increase privacy budget epsilon | DP persistence diagram mechanism · simulation, two circles, n=4000 | variability / bottleneck distance of private diagrams: log bottleneck distance approximately linear in log epsilon with slope -1 | Improved |
| increase sample size n | DP persistence diagram mechanism · simulation, two circles, epsilon=1 | variability / bottleneck distance of private diagrams: log d_B approx -log n + c | Improved |
| restrict persistence diagram space to at most M points with M=log n and discretize with N=n | exponential mechanism · theory | privacy-estimation error bound: O~_p((l+1)^2/(n epsilon) + (l+1)/n^{1/d}) | Improved |
Closest papers by meaning
- A Class of Topological Pseudodistances for Fast Comparison of Persistence Diagrams (AAAI 2024 · similarity 0.86)
- Differentially Private Graph Diffusion with Applications in Personalized PageRanks (NeurIPS 2024 · similarity 0.84)
- Differentially Private Set Representations (NeurIPS 2024 · similarity 0.84)
- Distributed Differentially Private Data Analytics via Secure Sketching (ICML 2025 · similarity 0.84)
- Differentially Private Equivalence Testing for Continuous Distributions and Applications (NeurIPS 2024 · similarity 0.84)
- Private Evolution Converges (NeurIPS 2025 · similarity 0.84)
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.
