In machine learning, hyperparameter optimization or tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. A hyperparameter is a parameter whose value is used to control the learning process. By contrast, the values of other parameters (typically node weights) are learned. .
Hyperparameter tuning optimizes a single target variable, also called the hyperparameter metric, that you specify. The accuracy of the model, as calculated from an evaluation pass, is a common metric. The metric must be a numeric value, and we can specify whether tuning on the model to maximize or minimize your metric. Starting of a job with hyperparameter tuning, establish the name of hyperparameter metric. The default name of the metric is training/hptuning/metric.These hyperparameters address below model design questions :