Exploration Strategies for Multi-trial NAS¶
Usage of Exploration Strategy¶
To use an exploration strategy, users simply instantiate an exploration strategy and pass the instantiated object to RetiariiExperiment
. Below is a simple example.
import nni.retiarii.strategy as strategy
exploration_strategy = strategy.Random(dedup=True) # dedup=False if deduplication is not wanted
Supported Exploration Strategies¶
NNI provides the following exploration strategies for multi-trial NAS. Users could also customize new exploration strategies.
Name |
Brief Introduction of Algorithm |
---|---|
Randomly sampling new model(s) from user defined model space. ( |
|
Sampling new model(s) from user defined model space using grid search algorithm. ( |
|
Generating new model(s) from generated models using regularized evolution algorithm . ( |
|
Sampling new model(s) from user defined model space using TPE algorithm . ( |
|
It uses PPO algorithm to sample new model(s) from user defined model space. ( |