Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or constant learning rate. On the one hand it averages weights, but it also has the property that, with a cyclical or constant learning rate, SGD proposals are approximately sampling from the loss surface of the network, leading to stochastic weights and helping to discover broader optima.
Source: Averaging Weights Leads to Wider Optima and Better GeneralizationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 5 | 10.87% |
Image Classification | 5 | 10.87% |
Domain Generalization | 3 | 6.52% |
Instance Segmentation | 2 | 4.35% |
Node Classification | 2 | 4.35% |
Question Answering | 2 | 4.35% |
Object Detection | 2 | 4.35% |
Language Modelling | 1 | 2.17% |
Clustering | 1 | 2.17% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |