MLS-C01 · Question #204
A machine learning (ML) specialist is using Amazon SageMaker hyperparameter optimization (HPO) to improve a model's accuracy. The learning rate parameter is specified in the following HPO…
The correct answer is C. Modify the HPO configuration as follows. Choose logarithmic scaling when you are searching a range that spans several orders of magnitude. For example, if you are tuning a Tune a linear learner model model, and you specify a range of values between .0001 and 1.0 for the learning_rate hyperparameter, searching…
Question
A machine learning (ML) specialist is using Amazon SageMaker hyperparameter optimization (HPO) to improve a model’s accuracy. The learning rate parameter is specified in the following HPO configuration:
During the results analysis, the ML specialist determines that most of the training jobs had a learning rate between 0.01 and 0.1. The best result had a learning rate of less than 0.01. Training jobs need to run regularly over a changing dataset. The ML specialist needs to find a tuning mechanism that uses different learning rates more evenly from the provided range between MinValue and MaxValue. Which solution provides the MOST accurate result?
Exhibits
Options
- AModify the HPO configuration as follows:
- BRun three different HPO jobs that use different learning rates form the following intervals
- CModify the HPO configuration as follows:
- DRun three different HPO jobs that use different learning rates form the following intervals
How the community answered
(35 responses)- A3% (1)
- B6% (2)
- C77% (27)
- D14% (5)
Explanation
Choose logarithmic scaling when you are searching a range that spans several orders of magnitude. For example, if you are tuning a Tune a linear learner model model, and you specify a range of values between .0001 and 1.0 for the learning_rate hyperparameter, searching uniformly on a logarithmic scale gives you a better sample of the entire range than searching on a linear scale would, because searching on a linear scale would, on average, devote 90 percent of your training budget to only the values between .1 and 1.0, leaving only 10 percent of your training budget for the values between .0001 and .1. https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning-define-ranges.html
Topics
Community Discussion
No community discussion yet for this question.