Research map / Federated learning and privacy / Communication-efficient FL
FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters
Hiro Ishii, Kenta Niwa, Hiroshi Sawada, Akinori Fujino, Noboru Harada, Rio Yokota
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 |
|---|---|---|---|
| replace simple parameter mixing (LocalNewton) with preconditioned mixing | FedPM (FOOF) · CIFAR10 alpha=0.1 | best test accuracy (%): 62.4 -> 68.6 | Improved |
| replace simple mixing with preconditioned mixing | FedPM (FOOF) · CIFAR100 alpha=0.1 | best test accuracy (%): 61.9 -> 63.1 | Improved |
| replace simple mixing with preconditioned mixing | FedPM (FOOF) · CIFAR10 alpha=1.0 | best test accuracy (%): 73.4 -> 74.8 | Improved |
| replace simple mixing with preconditioned mixing | FedPM (FOOF) · CIFAR100 alpha=1.0 | best test accuracy (%): 70.2 -> 68.4 | Hurt |
| use FedPM vs best first-order method | FedPM · CIFAR100 alpha=0.1 | best test accuracy (%): 58.2 -> 63.1 | Improved |
| use preconditioned mixing in strongly convex logistic regression (K=1) | FedPM · w8a and a9a | optimality gap | Improved |
| FedPM vs FedNL with single local update | FedPM · w8a and a9a | convergence | No clear effect |
| vary number of local epochs (1, 5, 10) with fixed 500 total epochs (ablation) | FedPM · CIFAR10 alpha=0.1 | best test accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCAFFOLD — SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML 2020) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 2025 · similarity 0.89)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.88)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.88)
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.88)
- FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates (ICML 2025 · similarity 0.88)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · 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.
