Research map / Federated learning and privacy / Communication-efficient FL
FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization
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 FedDR (and FedPD) instead of FedProx and FedAvg without user sampling | federated nonconvex training · synthetic non-iid datasets | training loss and accuracy | Helped |
| use FedDR with user sampling vs FedAvg | federated training with 10 of 30 users sampled · synthetic non-iid datasets | performance vs bytes communicated | Helped |
| use FedDR instead of FedAvg, FedProx, FedPD | federated training · FEMNIST | training loss and training accuracy | Helped |
| increase local SGD epochs to evaluate prox more exactly (lower inexactness) (ablation) | FedDR with l1 regularizer · FEMNIST composite | performance | Helped |
| use asynchronous update (asyncFedDR) instead of synchronous FedDR (ablation) | FedDR · MNIST, 20 users with simulated delays | training time to performance | Helped |
Closest papers by meaning
- Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization (ICLR 2025 · similarity 0.89)
- Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data (NeurIPS 2024 · similarity 0.88)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.88)
- Stabilized Proximal-Point Methods for Federated Optimization (NeurIPS 2024 · similarity 0.88)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.88)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 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.