Research map / Federated learning and privacy / Differential privacy
Sum Estimation under Personalized Local Differential Privacy
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies sum and mean estimation under personalized local differential privacy, where each user chooses their own privacy parameter, and gives improved error bounds over prior work.
Problem
Prior work on personalized local differential privacy (PLDP), where each user privatizes data with a possibly different privacy parameter, has failed to give meaningful error bounds for sum/mean estimation.
Approach
Theoretical treatment of sum/mean estimation under heterogeneous per-user privacy parameters in the local model, aiming to obtain meaningful error guarantees where previous analyses did not.
Closest papers by meaning
- Locally Private Gaussian Estimation (NeurIPS 2019 · similarity 0.90)
- Minimax Optimal Estimation of Approximate Differential Privacy on Neighboring Databases (NeurIPS 2019 · similarity 0.90)
- Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms (NeurIPS 2020 · similarity 0.89)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.89)
- Instance-optimal Mean Estimation Under Differential Privacy (NeurIPS 2021 · similarity 0.89)
- Exactly Minimax-Optimal Locally Differentially Private Sampling (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.