[ML] Support for multi-parameter loss functions in derivative aggregation and finding best splits #993
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
tveasey
added
review
>non-issue
>refactoring
v8.0.0
:ml/DataFrameAnalysis
v7.7.0
labels
valeriy42
reviewed
Feb 14, 2020
Comment on lines
+54
to
+55
| // We wrap the writer in another lambda which we know takes advantage | ||
| // of std::function small size optimization to avoid heap allocations. |
|
Thanks for the review @valeriy42. I've addressed all your feedback, can you take another look and let me know if you're happy? |
tveasey
added a commit
to tveasey/ml-cpp-1
that referenced
this pull request
Feb 17, 2020
…tion and finding best splits (elastic#993)
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Outdated suggestions cannot be applied.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 extends computing aggregate derivatives and solving for the highest quadratic gain split to support multi-parameter loss functions.
I experimented with various implementations. This version, which minimises the number of allocations by using memory mapped classes, proved to be much the most efficient.
This is the next step towards #982.