Professional Machine Learning Engineer

Question

A proof-of-concept (POC) deep learning model has recently been created. The overall architecture is satisfactory, but the values of a couple of hyperparameters still need to be determined. You want to use Vertex AI hyperparameter tuning to identify both the suitable embedding dimension for a categorical feature used by the model and the optimal learning rate. Configure these settings:

For the embedding dimension, set the type to INTEGER, with a minValue of 16 and a maxValue of 64.
For the learning rate, set the type to DOUBLE, with a minValue of 10e-05 and a maxValue of 10e-02.

You use the default Bayesian optimization tuning algorithm and want to maximize model accuracy. Training time is not a concern. How should the hyperparameter scaling for each hyperparameter and maxParallelTrials be set?

Explanation

An embedding dimension in the bounded 16–64 integer range is suited to linear scaling, whereas a positive learning rate spanning several orders of magnitude is suited to logarithmic scaling. Bayesian optimization improves later parameter selections using results from prior trials; a small parallel-trial setting maximizes the opportunity to use those results and therefore favors final model accuracy when elapsed training time is not a concern.

Learn more

Professional Machine Learning Engineer

AstroTutor

Notes

Readiness

QuestionQ20

Community Discussion