[
https://issues.apache.org/jira/browse/SPARK-3820?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Reza Zadeh updated SPARK-3820:
------------------------------
Comment: was deleted
(was: See previous comment on resolution.)
> Specialize columnSimilarity() without any threshold
> ---------------------------------------------------
>
> Key: SPARK-3820
> URL: https://issues.apache.org/jira/browse/SPARK-3820
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Reporter: Xiangrui Meng
> Assignee: Reza Zadeh
>
> `RowMatrix.columnSimilarities` calls `RowMatrix.columnSimilarity(0.0)` to
> compute the exact cosine similarities. It still requires sampling, which is
> unnecessary for this case. We should have a specialized version for it, in
> order to have a fair comparison with DIMSUM.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
