Avoid duplicating initial points when using vectorization #875
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
uri-granta
commented
Sep 19, 2024
| @@ -802,7 +802,7 @@ def target_function(x: TensorType) -> TensorType: # [N,V,D] -> [N, V] | |||
| return tf.concat(individual_func, axis=-1) # vectorize by repeating same function | |||
|
|
|||
| optimizer = batchify_vectorize( | |||
| generate_continuous_optimizer(num_initial_samples=1_000, num_optimization_runs=10), | |||
| generate_continuous_optimizer(num_initial_samples=20_000, num_optimization_runs=10), | |||
There was a problem hiding this comment.
This started failing for Ackley5 (but not the others) following the code change. The code itself is working as intended: beforehand it was generating 1000 initial points and duplicating them 5 times, whereas afterwards it was generating 5000 distinct points. However, the found maximizer was no longer good enough.
Increasing the number of initial points (significantly) fixes things, but there may be a better way.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Related issue(s)/PRs:
Summary
Fully backwards compatible: yes / no
PR checklist