Research map / Federated learning and privacy / Communication-efficient FL
Federated Learning Via Inexact ADMM
Shenglong Zhou, Geoffrey Ye Li
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 |
|---|---|---|---|
| use FedADMM instead of FedProx, FedSim, FedAlt, FedAvg | FL algorithms · large-scale problems, m=4000 | computational time: 728 -> 73 | Improved |
| increase global averaging period k0 | FedADMM · linear regression (Example 1) | communication rounds | Improved |
| increase global averaging period k0 | FedAvg, FedProx, FedAlt, FedSim · linear regression (Example 1) | communication rounds | Hurt |
| increase k0 | all five algorithms · both examples | computational time | Hurt |
| increase participation rate rho | all five algorithms · linear regression (Example 1) | communication rounds | Improved |
| increase participation rate rho | all five algorithms · logistic regression (Example 2) | computational time | Hurt |
| increase number of clients m | all five algorithms · linear regression (Example 1) | communication rounds | Improved |
| increase number of clients m | FedADMM · logistic regression (Example 2) | communication rounds | Improved |
Closest papers by meaning
- Beyond ADMM: A Unified Client-Variance-Reduced Adaptive Federated Learning Framework (AAAI 2023 · similarity 0.89)
- Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM (NeurIPS 2023 · similarity 0.87)
- Federated ADMM from Bayesian Duality (ICLR 2026 · similarity 0.87)
- Connecting Federated ADMM to Bayes (ICLR 2025 · similarity 0.86)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.85)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.85)
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.
