In step 2, we created  ContinuousParameterSpace to configure the search space for hyperparameter optimization:

ParameterSpace<Double> learningRateParam = new ContinuousParameterSpace(0.0001,0.01);

In the preceding case, the hyperparameter tuning process will select continuous values in the range (0.0001, 0.01) for the learning rate. Note that arbiter doesn't really automate the hyperparameter tuning process. We still need to specify the range of values or a list of options by which the hyperparameter tuning process takes place. In other words, we need to specify a search space with all the valid values for the tuning process to pick the best combination that can produce the best results. We have also mentioned IntegerParameterSpace, where the search space is an ordered space of integers between a maximum/minimum value.

Since there are multiple training instances with different configurations, it takes a while  to finish the hyperparameter optimization-tuning process. At the end, the best configuration will be returned.

In step 2, once we have defined our search space using ParameterSpace or OptimizationConfiguration, we need to add it to MultiLayerSpace or ComputationGraphSpace. These are the arbiter counterparts of DL4J's MultiLayerConfiguration and ComputationGraphConfiguration.

Then we added candidateGenerator using the candidateGenerator() builder method. candidateGenerator chooses candidates (various combinations of hyperparameters) for hyperparameter tuning. It can use different approaches, such as random search and grid search, to pick the next configuration for hyperparameter tuning. 

scoreFunction() specifies the evaluation metrics used for evaluation during the hyperparameter tuning process.

terminationConditions() is used to mention all termination conditions for the training instance. Hyperparameter tuning will then proceed with the next configuration in the sequence.