AWS Certified Machine Learning Engineer – Associate (MLA-C01) — Question 59

A company is building a deep learning model on Amazon SageMaker. The company uses a large amount of data as the training dataset. The company needs to optimize the model's hyperparameters to minimize the loss function on the validation dataset.
Which hyperparameter tuning strategy will accomplish this goal with the LEAST computation time?

Answer options

• A. Hyperband
• B. Grid search
• C. Bayesian optimization
• D. Random search

Correct answer: A

Explanation

Hyperband is designed to efficiently allocate resources for hyperparameter tuning by using adaptive resource allocation, which minimizes computation time compared to methods like grid search and random search. Grid search systematically evaluates all combinations, and random search explores randomly, both of which can be more time-consuming than Hyperband. Bayesian optimization is efficient but generally requires more computation than Hyperband due to its iterative nature.