Home / ML Associate practice test / Model Development / Question

Databricks Machine Learning Associate · free practice question

An engineer has four hyperparameters, each with many plausible values, and only enough budget to test a limited number of configurations. Which search method…

Exam-style question on Model Development from the free ML Associate practice test, with the answer and a full explanation below.

Updated November 10, 2026

Model Development

An engineer has four hyperparameters, each with many plausible values, and only enough budget to test a limited number of configurations. Which search method is usually more efficient than exhaustive grid search in this situation?

  1. ARandom search, because it can sample a fixed number of candidates without evaluating every possible combination
  2. BGrid search, because it always reaches the best model with fewer evaluations when the space has many unimportant parameters
  3. CManual search, because changing values by hand guarantees broader coverage of the parameter space than random sampling
  4. DFull enumeration, because evaluating the entire Cartesian product is the only budget-aware approach in high dimensions
  5. ELeaveOneOut search, because it removes one parameter value at a time until the best setting remains after elimination
Answer & explanation

Correct answer: A

WHY A: Random search lets the user control the evaluation budget directly and is often more efficient than grid search in larger spaces. WHY NOT B: Grid search can waste trials on unimportant dimensions. WHY NOT C: Manual search is not systematically more efficient. WHY NOT D: Full enumeration is usually the least budget-friendly option. WHY NOT E: LeaveOneOut is a cross-validation scheme, not a parameter search method.

Take the full ML Associate practice test free →

Would you pass today?

This question is one of 45 in the free, timed Databricks Machine Learning Associate practice test. Take it and get a section-by-section score.

Start the free test →