iRprop- local optimiser. #1459
Merged
iRprop- local optimiser. #1459
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
Codecov Report
@@ Coverage Diff @@
## master #1459 +/- ##
=========================================
Coverage 100.00% 100.00%
=========================================
Files 95 96 +1
Lines 9300 9370 +70
=========================================
+ Hits 9300 9370 +70
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
MichaelClerx
force-pushed
the
1105-irpropmin
branch
from
8873783 to
b889d91
Compare
DavAug
approved these changes
Aug 17, 2022
There was a problem hiding this comment.
Looks very good to me, @MichaelClerx
I agree with not exposing the hyperparameters for now, given that according to the literature the algorithm appears to be quite robust to changes in them.
I just have minor comments. Happy for this to be merged
|
Thanks @DavAug ! |
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Outdated suggestions cannot be applied.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.
See #1105
Local gradient using optimiser with adaptive step size.
Seems to work pretty well
https://doi.org/10.1016/S0925-2312(01)00700-7
The easiest to read psuedo code for this algorithm is in a figure in the paper above.
Note that the
< 0/> 0is deliberate: the step size is not updated for= 0.