Stochastic Optimization
Polyak Averaging
Polyak Averaging is an optimization technique that sets final parameters to an average of (recent) parameters visited in the optimization trajectory. Specifically if in $t$ iterations we have parameters $\theta_{1}, \theta_{2}, \dots, \theta_{t}$, then Polyak Averaging suggests setting
$$ \theta_t =\frac{1}{t}\sum_{i}\theta_{i} $$
Image Credit: Shubhendu Trivedi & Risi Kondor
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 2 | 16.67% |
| Depth Estimation | 1 | 8.33% |
| Image Segmentation | 1 | 8.33% |
| Language Modelling | 1 | 8.33% |
| Monocular Depth Estimation | 1 | 8.33% |
| Pose Estimation | 1 | 8.33% |
| Reinforcement Learning | 1 | 8.33% |
| Semantic Segmentation | 1 | 8.33% |
| General Classification | 1 | 8.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
