Avoid unnecessary memory allocation for covariance downdate in SGPR prediction strategy #2559
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
jacobrgardner
approved these changes
Aug 7, 2024
There was a problem hiding this comment.
@gpleiss should we cut a release with this at some point before merging any 2.0 breaking changes on main?
|
@jacobrgardner yeah, we'll need at least one more pre-2.0 minor release to include new deprecation warnings. I'm changing this PR to be merged into |
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Outdated suggestions cannot be applied.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.
Problem
Currently in the SGPR prediction strategy the downdate term in the predictive covariance (shape
num_test x num_test) is constructed densely in memory causing unnecessary memory overhead.Fix
Replaced the downdate term with a
linear_operator.MatmulLinearOperator.