force batch sizes of ReshufflingBatchSubsampling to have the same size
#228
+32
−13
Conversation
This file contains hidden or 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
Contributor
|
AdvancedVI.jl documentation for PR #228 is available at: |
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Outdated suggestions cannot be applied.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.
This addresses #224 .
The PR essentially drops the last batch if it has a size different from
batchsize. This is enforced only for estimating the gradients. So the behavior ofestimate_objectiveis unchanged. Dropping the last batch could introduce a slight bias in the algorithms, but it should be minimal as long as the number of batches is sufficiently large (which is the only case where subsampling makes sense anyway.)