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.

Sign up for GitHub

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

Jump to bottom

Small vs. large dataset meaning in the context of s_decay #5

Open

ogencoglu opened this issue Sep 1, 2024 · 0 comments

ogencoglu commented Sep 1, 2024 •

edited

Loading

The option s_decay is a bit like a weight-decay term that empirically is helpful for smaller datasets. We use a default of 0.01 in all our experiments. For larger datasets, smaller values (even 0.0) often worked as well.

What does small and large dataset mean in this context?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment