[SPARK-58550][ML] Delay GaussianMixture aggregation allocations - #57750
Closed
zhengruifeng wants to merge 1 commit into
Closed
[SPARK-58550][ML] Delay GaussianMixture aggregation allocations#57750zhengruifeng wants to merge 1 commit into
zhengruifeng wants to merge 1 commit into
Conversation
zhengruifeng
changed the title
zhengruifeng
marked this pull request as draft
August 4, 2026 09:00
zhengruifeng
force-pushed
the
gaussian-mixture-lazy-aggregate-dev3
branch
from
August 5, 2026 04:00
170a44c to
4df51f5
Compare
zhengruifeng
marked this pull request as ready for review
August 5, 2026 07:04
HyukjinKwon
approved these changes
Aug 5, 2026
uros-b
approved these changes
Aug 5, 2026
Member
|
Thank you @zhengruifeng and @HyukjinKwon! |
uros-b
pushed a commit
that referenced
this pull request
Aug 5, 2026
### What changes were proposed in this pull request? This PR delays allocation of `ExpectationSum` in `GaussianMixture` until an aggregation partition receives its first point. Empty partitions and intermediate tree branches use `null` as the aggregation identity. ### Why are the changes needed? The previous `treeAggregate` zero value eagerly allocated the mixture weights, means, and one dense covariance matrix per cluster. That can be substantial for large models and is also serialized to every partition, even empty ones. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Not run (not requested). Added coverage using an RDD with an empty partition. Static checks: `git diff --check`, ASCII scan, and changed-line length scan. ### Was this patch authored or co-authored using generative AI tooling? Generated-by: Codex (GPT-5) Closes #57750 from zhengruifeng/gaussian-mixture-lazy-aggregate-dev3. Authored-by: Ruifeng Zheng <ruifengz@apache.org> Signed-off-by: Uros Bojanic <221401595+uros-b@users.noreply.github.com> (cherry picked from commit 811e666) Signed-off-by: Uros Bojanic <221401595+uros-b@users.noreply.github.com>
Member
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
What changes were proposed in this pull request?
This PR delays allocation of
ExpectationSuminGaussianMixtureuntil an aggregation partition receives its first point. Empty partitions and intermediate tree branches usenullas the aggregation identity.Why are the changes needed?
The previous
treeAggregatezero value eagerly allocated the mixture weights, means, and one dense covariance matrix per cluster. That can be substantial for large models and is also serialized to every partition, even empty ones.Does this PR introduce any user-facing change?
No.
How was this patch tested?
Not run (not requested). Added coverage using an RDD with an empty partition. Static checks:
git diff --check, ASCII scan, and changed-line length scan.Was this patch authored or co-authored using generative AI tooling?
Generated-by: Codex (GPT-5)