-
Hi LiY,
Thank you for reaching out with your observation regarding the question on warm start hyperparameter tuning.
You are correct. According to the official AWS SageMaker AI documentation, a warm start hyperparameter tuning job requires that the objective metric in the new tuning job must be the same as in the previous jobs. Since the scenario states that the objective metric was changed to recall, warm start tuning cannot be used.
Because of this restriction, the best approach in such a case is to start a new hyperparameter tuning job without referencing previous results while continuing to use Bayesian optimization to explore the expanded hyperparameter range efficiently.
We appreciate your attention to detail and for bringing this to our attention. We have updated the question scenario accordingly, and this update will reflect on the portal soon.
If you have any more questions or feedback, please don’t hesitate to contact us.
Best,
Irene @ Tutorials Dojo
