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 | 13 | 16.05% |
| Classification | 5 | 6.17% |
| Time Series Analysis | 4 | 4.94% |
| Computational Efficiency | 4 | 4.94% |
| Reinforcement Learning (RL) | 3 | 3.70% |
| General Classification | 3 | 3.70% |
| Language Modelling | 2 | 2.47% |
| Knowledge Tracing | 2 | 2.47% |
| Multi-agent Reinforcement Learning | 2 | 2.47% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
