Learning Rate Schedules
Exponential Decay
Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function:
$$ \text{lr} = \text{lr}_{0}\exp\left(-kt\right) $$
Image Credit: Suki Lau
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 11 | 22.45% |
| Time Series | 3 | 6.12% |
| General Classification | 3 | 6.12% |
| Knowledge Tracing | 2 | 4.08% |
| Multi-agent Reinforcement Learning | 2 | 4.08% |
| Face Recognition | 2 | 4.08% |
| Change Detection | 2 | 4.08% |
| Two-sample testing | 2 | 4.08% |
| 3D Reconstruction | 1 | 2.04% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
