Fix gradient scaling when subsampling #533
Merged
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
fritzo
commented
Nov 8, 2017
| assert_equal(actual_grads, expected_grads, prec=precision) | ||
|
|
||
|
|
||
| # The golden values below (mu_q_expected/log_sig_q_expected/) need to be updated each time |
There was a problem hiding this comment.
This test was moved from test_gradient_step.py. The only changes were to add ids to the @pytest.mark.parameterize decorators.
martinjankowiak
approved these changes
Nov 8, 2017
This was referenced Nov 10, 2017
Merged
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Outdated suggestions cannot be applied.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.
Fixes #531
This implements a quick-and-dirty fix for double counted
site["scale"]when subsampling. This corresponds to Solution 2 in #531. The author would like to merge this PR first, and later clean up by implementing Solution 1 in #531.Tested
Added a regression test in
tests/infer/test_gradient.pythat compares gradient estimates with and without subsampling. Results are: