[
https://issues.apache.org/jira/browse/SPARK-10329?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xiangrui Meng updated SPARK-10329:
----------------------------------
Summary: Cost RDD in k-means|| initialization is not storage-efficient
(was: Cost RDD in k-means initialization is not storage-efficient)
> Cost RDD in k-means|| initialization is not storage-efficient
> -------------------------------------------------------------
>
> Key: SPARK-10329
> URL: https://issues.apache.org/jira/browse/SPARK-10329
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Affects Versions: 1.3.1, 1.4.1, 1.5.0
> Reporter: Xiangrui Meng
> Labels: clustering
>
> Currently we use `RDD[Vector]` to store point cost during k-means||
> initialization, where each `Vector` has size `runs`. This is not
> storage-efficient because `runs` is usually 1 and then each record is a
> Vector of size 1. What we need is just the 8 bytes to store the cost, but we
> introduce two objects (DenseVector and its values array), which could cost 16
> bytes. That is 200% overhead. Thanks [~Grace Huang] and Jiayin Hu from Intel
> for reporting this issue!
> There are several solutions:
> 1. Use `RDD[Array[Double]]` instead of `RDD[Vector]`, which saves 8 bytes per
> record.
> 2. Use `RDD[Array[Double]]` but batch the values for storage, e.g. each
> `Array[Double]` object covers 1024 instances, which could remove most of the
> overhead.
> Besides, using MEMORY_AND_DISK instead of MEMORY_ONLY could prevent cost RDDs
> kicking out the training dataset from memory.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
