I am using Bayesian hyperparameter optimization for LSTM hyperparameters. This manages to find an optimum set of hyperparameters in much fewer iterations than a grid search.

My problem is that I have a large amount of training data ~14000 samples, each with their own time-series sequence since I am using an LSTM model. This large amount is still slowing the training process substantially.

  1. Is it possible to trim the training data and optimize hyperparameters on a subset?
  2. Will this skew the hyperparameter optimizer or will it still manage to find an optimum?
  3. Is there any research that has been done on this kind of idea?

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.