You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Feynman Liang (JIRA)" <ji...@apache.org> on 2015/07/10 07:42:04 UTC
[jira] [Commented] (SPARK-8520) Improve GLM's scalability on number
of features
[ https://issues.apache.org/jira/browse/SPARK-8520?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14621780#comment-14621780 ]
Feynman Liang commented on SPARK-8520:
--------------------------------------
To clarify, is this [vector free LBGFS | http://papers.nips.cc/paper/5333-large-scale-l-bfgs-using-mapreduce.pdf] the solution proposed in 2?
> Improve GLM's scalability on number of features
> -----------------------------------------------
>
> Key: SPARK-8520
> URL: https://issues.apache.org/jira/browse/SPARK-8520
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Affects Versions: 1.4.0
> Reporter: Xiangrui Meng
> Assignee: Xiangrui Meng
> Priority: Critical
> Labels: advanced
>
> MLlib's GLM implementation uses driver to collect gradient updates. When there exist many features (>20 million), the driver becomes the performance bottleneck. In practice, it is common to see a problem with a large feature dimension, resulting from hashing or other feature transformations. So it is important to improve MLlib's scalability on number of features.
> There are couple possible solutions:
> 1. still use driver to collect updates, but reduce the amount of data it collects at each iteration.
> 2. apply 2D partitioning to the training data and store the model coefficients distributively (e.g., vector-free l-bfgs)
> 3. parameter server
> 4. ...
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org