[
https://issues.apache.org/jira/browse/SPARK-7210?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14608976#comment-14608976
]
Feynman Liang commented on SPARK-7210:
--------------------------------------
Some relevant links:
[A R cookbook
recipe|http://thirteen-01.stat.iastate.edu/snoweye/hpsc/?item=cookbook&subitem=ex_mvn]
describing and implementing mvn densities using Cholesky decomposition.
[Another R reference with the same implementation as
above|http://gallery.rcpp.org/articles/dmvnorm_arma/]
[The C++ code called by R's `mvnfast` package
|https://github.com/mfasiolo/mvnfast/blob/master/src/rmvnCpp.cpp]
> Test matrix decompositions for speed vs. numerical stability for Gaussians
> --------------------------------------------------------------------------
>
> Key: SPARK-7210
> URL: https://issues.apache.org/jira/browse/SPARK-7210
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Reporter: Joseph K. Bradley
> Priority: Minor
>
> We currently use SVD for inverting the Gaussian's covariance matrix and
> computing the determinant. SVD is numerically stable but slow. We could
> experiment with Cholesky, etc. to figure out a better option, or a better
> option for certain settings.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
