You use Azure Machine Learning to train a model. You must use a sampling method for tuning hyperparameters. The sampling method must pick samples based on how the model performed with previous…

The correct answer is B. Bayesian. Bayesian sampling is the correct choice because it uses a probabilistic model (specifically a Gaussian process) to select the next set of hyperparameters based on how previous samples performed. It tries to pick values that are likely to improve the primary metric, making it an…

Explore data and run experiments

Question

You use Azure Machine Learning to train a model. You must use a sampling method for tuning hyperparameters. The sampling method must pick samples based on how the model performed with previous samples. You need to select a sampling method. Which sampling method should you use?

Options

AGrid
BBayesian
CRandom

How the community answered

(58 responses)

A
3% (2)
B
88% (51)
C
9% (5)

Explanation

Bayesian sampling is the correct choice because it uses a probabilistic model (specifically a Gaussian process) to select the next set of hyperparameters based on how previous samples performed. It tries to pick values that are likely to improve the primary metric, making it an intelligent, iterative approach. Grid sampling exhaustively tries every combination of discrete values without learning from prior results. Random sampling selects values randomly from the search space and also does not consider past performance. Only Bayesian sampling adapts its choices based on previous trial outcomes, which is exactly what the requirement describes.

Topics

#Hyperparameter tuning#Bayesian optimization#Azure Machine Learning#Model training

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice