EFF Optimize memory usage for sparse matrices in LLE (Hessian, Modified and LTSA) #28096
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
|
Could you add an entry in the changelog |
glemaitre
reviewed
Jan 13, 2024
glemaitre
reviewed
Jan 13, 2024
glemaitre
reviewed
Jan 13, 2024
removing double loop Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
resolving loop for sparse matrix Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
|
Sorry @giorgioangel I did not have time to follow-up before the release. I'll add the milestone for 1.6 and make a review. I'll sort out any conflict and ping someone else for a second review. |
glemaitre
approved these changes
May 20, 2024
OmarManzoor
approved these changes
Jun 27, 2024
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Outdated suggestions cannot be applied.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.
What does this implement/fix? Explain your changes.
This PR optimizes memory management with sparse matrices when using Modified Locally Linear Embedding.
Before this PR, a numpy NxN array was created, filled, and then converted to sparse. The creation of the said array can require huge memory when dealing with a large dataset.
On the dataset I was working with, the algorithm tried to allocate 400GB of RAM lol...
In the current PR, when M_sparse is true, the algorithm creates directly a sparse matrix, greatly reducing the memory requirements.