[ https://issues.apache.org/jira/browse/SPARK-17137?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15429025#comment-15429025 ]
DB Tsai edited comment on SPARK-17137 at 8/19/16 11:16 PM: ----------------------------------------------------------- Currently, for LiR or BLOR, we always do `Vector.compressed` when creating the models which is optimized for space, but computation. We need to investigate the trade-off. was (Author: dbtsai): Currently, for LiR or BLOR, we always do `Vector.compressed` which is optimized for space, but computation. We need to investigate the trade-off. > Add compressed support for multinomial logistic regression coefficients > ----------------------------------------------------------------------- > > Key: SPARK-17137 > URL: https://issues.apache.org/jira/browse/SPARK-17137 > Project: Spark > Issue Type: Sub-task > Components: ML > Reporter: Seth Hendrickson > Priority: Minor > > For sparse coefficients in MLOR, such as when high L1 regularization, it may > be more efficient to store coefficients in compressed format. We can add this > option to MLOR and perhaps to do some performance tests to verify > improvements. -- 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