Graphs from overparameterized broadness script #16
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I finally got around to adding the graphs I mentioned in #15. Here's what they look like for seeds 0 through 4:
So 0, 3 and 4 look very similar, but 1 and 2 are different.
My understanding is that this basically answers the question this was looking at? That is, my understanding is that the point of this was to answer "if we train an overparameterized model, do we reliably get the same result" and this says that no we don't. But I'm not confident I understand well.