Amazon SageMaker Automatic Model Tuning now supports 30x higher limits for categorical hyperparameters

Amazon SageMaker Automatic Model Tuning now supports 30x higher limits for the number of categorical hyperparameter values that can be searched per tuning job.

SageMaker Automatic Model Tuning allows you to find the most accurate version of your machine learning model by searching for the optimal set of hyperparameter configurations. Starting today, you can now run tuning jobs with up to 900 categorical values, which is 30 times the previous limit of 30 categorical values in total. The ability to use an increased number of total categorical values per tuning job enables exploring more hyperparameter combinations, and it helps to optimize the tradeoff between wall-clock time, predictive performance, and overall cost.

When more combinations are explored, the chances of finding high quality hyperparameter configurations are increased, which can improve the quality of your model. This higher number of categorical hyperparameters allows using SageMaker Automatic Model Tuning for use cases such as Neural Architecture Search, which typically requires a larger number of categorical hyperparameters to be tuned.

Increased limits for SageMaker Automatic Model Tuning are now available in all commercial AWS Regions and applicable to all tuning jobs. You can find the new limits in the resource limits page, the hyperparameter ranges definition page and the warm start tuning job page. You can launch SageMaker Automatic Model Tuning jobs with higher limits in AWS Console, using AWS SDK or Sagemaker SDK. To learn more, please visit the SageMaker Automatic Model Tuning web page.