I was originally doing a grid search for my parameter optimization and with 7 parameters being optimized, it would take ages. So I am choosing to use hyperopt at this point.

I am however confused on what space function to choose for my learning rate and learning rate decay options. In my grid search, I was considering look at learning rate values of [0.1, 0.01, 0.001, 0.0001] and learning rate decay values of [0.9, 0.99, 0.999, 0.9997].

I was thinking about hp.uniform for the learning rate decay, but would there be a better option? I have no inclination into where the best model will be. Also for learning rate in this range what would be the best option? I am new to hyperopt but project lead wants me to utilize it.

Would hp.loguniform be appropriate for either of these?

Any help would be greatly appreciated.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.