search

rk2900 / DRSA

Deep Recurrent Survival Analysis, an auto-regressive deep model for time-to-event data analysis with censorship handling. An implementation of our AAAI 2019 paper and a benchmark for several (Python) implemented survival analysis methods.
139 stars 57 forks source link

FIND_PARAMETERS #8

Closed cwzhou closed 3 years ago

cwzhou commented 3 years ago

Hello,

I was wondering how you tuned your hyperparameters for DRSA. I saw that in BASE_MODEL.py, there was a "FIND_PARAMETERS" argument but no corresponding definition or function for that. I didn't see in your paper a section regarding how you chose the hyperparameters that you did.

Thank you for your time!

rk2900 commented 3 years ago

We use grid search over the learning rates and regularization parameters for all the compared methods.

cwzhou commented 3 years ago

Would you be able to share your scripts for the hyperparameter tuning?