Exam DP-100 topic 3 question 113 discussion

Actual exam question from Microsoft's DP-100

Question #: 113
Topic #: 3

HOTSPOT
-

You use Azure Machine Learning to implement hyperparameter tuning.

Training runs must terminate when the primary metric is lowered by 25 percent or more compared to the best performing run.

You need to configure an early termination policy to terminate training jobs.

Which values should you use? To answer, select the appropriate options in the answer area.

NOTE: Each correct selection is worth one point.

Show Suggested Answer

Suggested Answer:

by Tommo565 at March 21, 2023, 2:12 p.m.

Comments

Submit Cancel

oakmm

Highly Voted 1 year, 2 months ago

would Truncation Selection and Truncation_percentage be better answer?

upvoted 5 times

...

evangelist

Most Recent 4 days, 10 hours ago

Bandit Policy: The Bandit policy is an early termination policy that stops poorly performing runs early based on the ratio of the performance of the run to the best performing run. This is suitable for the given requirement as it compares the primary metric of each run against the best run and terminates those that fall below a certain threshold. slack_factor: The slack_factor parameter defines the allowable slack (tolerance) as a ratio. A slack_factor of 0.75 means that runs which perform worse than 75% of the best run (i.e., lowered by 25% or more) will be terminated.

upvoted 1 times

...

Mal42

9 months, 3 weeks ago

On exam 18 Aug 2023

upvoted 4 times

...

snegnik

1 year ago

Bandit policy is based on slack factor/slack amount and evaluation interval. Bandit policy ends a job when the primary metric isn't within the specified slack factor/slack amount of the most successful job.

upvoted 2 times

...

Tommo565

1 year, 2 months ago

Correct: https://learn.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters#bandit-policy

upvoted 3 times

...

Exam DP-100 All Questions

View all questions & answers for the DP-100 exam