[ https://issues.apache.org/jira/browse/SPARK-11560?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14997103#comment-14997103 ]
Joseph K. Bradley commented on SPARK-11560: ------------------------------------------- Do we want to keep the implementation for the Pipelines API? We had worked on stacking models for linear methods (to do many runs at once) to amortize overhead, and this is the same kind of effort. It should be helpful in some problem domains. Has there been evidence that it's rarely useful? > Optimize KMeans implementation > ------------------------------ > > Key: SPARK-11560 > URL: https://issues.apache.org/jira/browse/SPARK-11560 > Project: Spark > Issue Type: Improvement > Components: MLlib > Affects Versions: 1.7.0 > Reporter: Xiangrui Meng > > After we dropped `runs`, we can simplify and optimize the k-means > implementation. -- 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