Research map / Federated learning and privacy / Differential privacy
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
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 user sampling and aggregate sampled users' contributions for central-model privacy | Federated private ADMM · Federated user-level DP (central model) | RDP epsilon: m^2/n^2; 1/m^2; 1/n^2 | Helped |
| Use a random-walk decentralized model with privacy amplification by iteration | Fully decentralized private ADMM · Fully decentralized user-level network DP | network RDP epsilon: O(\ln n / n^2) | Helped |
| Increase sampled users per round from one toward full participation | Federated private ADMM · Federated private ADMM | squared error: m=n; m=1 | Helped |
Closest papers by meaning
- Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions (AAAI 2024 · similarity 0.90)
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.90)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.89)
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 2024 · similarity 0.89)
- DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing (ICML 2025 · similarity 0.89)
- Locally Differentially Private Decentralized Stochastic Bilevel Optimization with Guaranteed Convergence Accuracy (ICML 2024 · similarity 0.88)
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.