Research map / Federated learning and privacy / Differential privacy
Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
Leheng Cai, Qirui Hu, Juntao Sun, Shuyuan Wu
Read the paperCheck your idea against 137,217 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.
Builds a time-uniform asymptotic confidence sequence for quantiles under local differential privacy by combining dynamically chained parallel SGD with randomized response.
Problem
Constructing valid, time-uniform confidence sequences for quantiles of data collected under local differential privacy (LDP), while estimating the quantile and its variance online.
Approach
Combines dynamically chained parallel stochastic gradient descent (P-SGD) with a randomized response mechanism so that the privatized stream yields the quantile estimate and its variance, with a strong Gaussian approximation supporting time-uniform asymptotic confidence sequences.
Experimental setup
Builds on: stochastic gradient descent randomized response
Closest papers by meaning
- Lightweight Protocols for Distributed Private Quantile Estimation (ICML 2025 · similarity 0.89)
- Differentially Private Quantiles with Smaller Error (NeurIPS 2025 · similarity 0.88)
- Minimax Optimal Two-Sample Testing under Local Differential Privacy (NeurIPS 2026 · similarity 0.87)
- Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy (ICLR 2024 · similarity 0.87)
- Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms (ICML 2025 · similarity 0.87)
- Universal Exact Compression of Differentially Private Mechanisms (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.
