AutoML
Hyper-parameter optimization
Introduced by Bergstra et al. in Algorithms for Hyper-Parameter OptimizationIn machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a learning algorithm.
Source: Algorithms for Hyper-Parameter OptimizationPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Bayesian Optimization | 26 | 21.67% |
| BIG-bench Machine Learning | 13 | 10.83% |
| Benchmarking | 7 | 5.83% |
| Reinforcement Learning (RL) | 5 | 4.17% |
| Federated Learning | 4 | 3.33% |
| Fairness | 4 | 3.33% |
| Image Classification | 4 | 3.33% |
| Interpretable Machine Learning | 3 | 2.50% |
| Knowledge Graphs | 2 | 1.67% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
