Which of the following is a common limitation of grid search compared to random search?

It requires a probabilistic model of the objective

It may miss optimal values that lie between the grid points

It cannot handle categorical hyperparameters

It is always slower than random search

What does the `fmin` function return after the optimization completes?

The trained model with the best hyperparameters

The best hyperparameters as a dictionary

The loss value of the best trial only

A list of all evaluated hyperparameters and their losses

DatabricksCertified Machine Learning Associate

Domain 3Objective 4

Hyperparameter Tuning MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 3)

Part of the Section 3: Model Development domain, which makes up ~23% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~8–14 in this domain), expect 2–4 from this objective — we provide 24 practice questions to prepare you well beyond it. (estimate)

24questions here

5free pages

11concepts

Questions 11–15

11foundation · easy
Which Hyperopt `hp` function should you use to define a search space for a hyperparameter that is a real number uniformly distributed between 0 and 1?
Select an answer first
12foundation · easy
Which of the following is a common limitation of grid search compared to random search?
Select an answer first
13foundation · easy
Which Hyperopt algorithm is commonly used for Bayesian optimization and is based on the Tree-structured Parzen Estimator?
Select an answer first
14foundation · easy
What does the `fmin` function return after the optimization completes?
Select an answer first
15foundation · easy
Which Hyperopt `hp` function is appropriate for defining a search space that selects one of several discrete categorical options, such as 'linear', 'rbf', or 'poly' for a kernel type?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MACHINE-LEARNING-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “MACHINE-LEARNING-ASSOCIATE” is a trademark of its owner, used for identification only.

Hyperparameter Tuning MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 3)

Questions 11–15

Which Hyperopt `hp` function should you use to define a search space for a hyperparameter that is a real number uniformly distributed between 0 and 1?

Which of the following is a common limitation of grid search compared to random search?

Which Hyperopt algorithm is commonly used for Bayesian optimization and is based on the Tree-structured Parzen Estimator?

What does the `fmin` function return after the optimization completes?

Which Hyperopt `hp` function is appropriate for defining a search space that selects one of several discrete categorical options, such as 'linear', 'rbf', or 'poly' for a kernel type?

Keep studying — Section 3: Model Development