Population Based Training, or PBT, is an optimization method for finding parameters and hyperparameters, and extends upon parallel search methods and sequential optimisation methods. It leverages information sharing across a population of concurrently running optimisation processes, and allows for online propagation/transfer of parameters and hyperparameters between members of the population based on their performance. Furthermore, unlike most other adaptation schemes, the method is capable of performing online adaptation of hyperparameters -- which can be particularly important in problems with highly non-stationary learning dynamics, such as reinforcement learning settings. PBT is decentralised and asynchronous, although it could also be executed semi-serially or with partial synchrony if there is a binding budget constraint.
Source: Population Based Training of Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Reinforcement Learning (RL) | 4 | 17.39% |
Classification | 2 | 8.70% |
Image Generation | 1 | 4.35% |
Adversarial Robustness | 1 | 4.35% |
Fairness | 1 | 4.35% |
Graph Classification | 1 | 4.35% |
Graph Learning | 1 | 4.35% |
Link Prediction | 1 | 4.35% |
Node Classification | 1 | 4.35% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |