Dynamic algorithm configuration (DAC) is capable of generalizing over prior optimization approaches, as well as handling optimization of hyperparameters that need to be adjusted over multiple time-steps.
Image Source: Biedenkapp et al.
Source: Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic FrameworkPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Reinforcement Learning (RL) | 4 | 6.78% |
Domain Adaptation | 3 | 5.08% |
Dialogue Act Classification | 3 | 5.08% |
Image Segmentation | 2 | 3.39% |
Semantic Segmentation | 2 | 3.39% |
Benchmarking | 2 | 3.39% |
Classification | 2 | 3.39% |
Image Classification | 2 | 3.39% |
Imitation Learning | 1 | 1.69% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |