Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Validation Samplers #144

Open
jbgao opened this issue Jul 18, 2023 · 0 comments
Open

Validation Samplers #144

jbgao opened this issue Jul 18, 2023 · 0 comments

Comments

@jbgao
Copy link

jbgao commented Jul 18, 2023

Let us take DeepAREstimator as an example: The estimator defines

self.validation_sampler = ValidationSplitSampler(min_future=prediction_length)

However a ValidationSplitSampler always only takes the last block from the given time series, that means only one block of time series was used to calculate validation error. This clearly is not a good indicator in training.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant