Stochastic Optimization
Local SGD
Introduced by Stich in Local SGD Converges Fast and Communicates LittleLocal SGD is a distributed training technique that runs SGD independently in parallel on different workers and averages the sequences only once in a while.
Source: Local SGD Converges Fast and Communicates Little
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Federated Learning | 25 | 49.02% |
| Language Modeling | 4 | 7.84% |
| Language Modelling | 4 | 7.84% |
| Image Classification | 4 | 7.84% |
| Edge-computing | 3 | 5.88% |
| BIG-bench Machine Learning | 2 | 3.92% |
| Blocking | 2 | 3.92% |
| Multi-Task Learning | 1 | 1.96% |
| Large Language Model | 1 | 1.96% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
