[
https://issues.apache.org/jira/browse/SPARK-8514?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14717696#comment-14717696
]
Jerome commented on SPARK-8514:
-------------------------------
I have a draft of the LU Decomposition in BlockMatrix.scala
https://github.com/nilmeier/spark/blob/SPARK-8514_LU_factorization
https://github.com/nilmeier/spark/blob/SPARK-8514_LU_factorization/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
Only one unit test so far:
https://github.com/nilmeier/spark/blob/SPARK-8514_LU_factorization/mllib/src/test/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrixSuite.scala
The method here is slightly different than the previously proposed method in
that it preforms large block matrices for large BlockMatrix.multiply
operations. I'll be adding documentation shortly to github to describe the
method.
Cheers, J
> LU factorization on BlockMatrix
> -------------------------------
>
> Key: SPARK-8514
> URL: https://issues.apache.org/jira/browse/SPARK-8514
> Project: Spark
> Issue Type: New Feature
> Components: MLlib
> Reporter: Xiangrui Meng
> Labels: advanced
> Attachments: BlockMatrixSolver.pdf, BlockPartitionMethods.py,
> BlockPartitionMethods.scala, LUBlockDecompositionBasic.pdf, testScript.scala
>
>
> LU is the most common method to solve a general linear system or inverse a
> general matrix. A distributed version could in implemented block-wise with
> pipelining. A reference implementation is provided in ScaLAPACK:
> http://netlib.org/scalapack/slug/node178.html
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
