Research map / Federated learning and privacy / Communication-efficient FL
FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
Yuki Takezawa, Anastasia Koloskova, Xiaowen Jiang, Sebastian U Stich
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 |
|---|---|---|---|
| add SCAFFOLD-style bias-correcting control variates before the LMO (ablation) | LocalMuon · Heterogeneous FL (FashionMNIST LeNet, CIFAR-10 ResNet-18) | test accuracy | Improved |
| add bias correction to LocalMuon (ablation) | LocalMuon · Homogeneous FL | test accuracy | No clear effect |
| use Muon LMO instead of Adam locally | FedAvg/SCAFFOLD · FashionMNIST and CIFAR-10 | test accuracy | Improved |
| increase Newton-Schulz iterations from 0 to 1 (ablation) | FedMuon · FashionMNIST LeNet | test accuracy | Improved |
| more Newton-Schulz iterations (T=4 homogeneous, T=2 heterogeneous best) (ablation) | FedMuon · FashionMNIST LeNet | test accuracy | Mixed |
Closest papers by meaning
- From SGD to Muon: Adaptive Optimization via Schatten-p Norms (NeurIPS 2026 · similarity 0.86)
- FADAS: Towards Federated Adaptive Asynchronous Optimization (ICML 2024 · similarity 0.85)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.85)
- FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update (AAAI 2024 · similarity 0.85)
- FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates (ICML 2025 · similarity 0.85)
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 2025 · 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.
