[
https://issues.apache.org/jira/browse/SPARK-7210?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14622937#comment-14622937
]
Joseph K. Bradley commented on SPARK-7210:
------------------------------------------
Reza pointed out that R requires a positive definite matrix so no degeneracies
are allowed:
[https://stat.ethz.ch/R-manual/R-devel/library/MASS/html/mvrnorm.html]
We can do the same, and fix degeneracies with smoothing.
This does not answer the question of which matrix decomposition is best, but
solves part of the issue.
> 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]
