Research map / Federated learning and privacy / Communication-efficient FL
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Prashant Khanduri, PRANAY SHARMA, Haibo Yang, Mingyi Hong, Jia Liu, Ketan Rajawat, Pramod Varshney
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 |
|---|---|---|---|
| increase local updates from I=67 to I=536 at fixed b=8 (ablation) | STEM · MNIST high heterogeneity | samples per worker to reach 96-97% accuracy: 5000-6000 -> more than 25000 | Hurt |
| use STEM instead of FedAvg and SCAFFOLD | CIFAR-10 CNN, moderate and high heterogeneity · CIFAR-10 | training loss and test accuracy vs communication rounds | Improved |
| small batch with many local updates (b=8, I=61) vs large batch with few updates (b=64, I=7) (ablation) | STEM · CIFAR-10 moderate heterogeneity | convergence | No clear effect |
Closest papers by meaning
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 2025 · similarity 0.90)
- Momentum Benefits Non-iid Federated Learning Simply and Provably (ICLR 2024 · similarity 0.89)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.89)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.88)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 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.
