flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF GitHub Bot (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (FLINK-2131) Add Initialization schemes for K-means clustering
Date Tue, 17 Jan 2017 11:42:27 GMT

    [ https://issues.apache.org/jira/browse/FLINK-2131?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15825913#comment-15825913

ASF GitHub Bot commented on FLINK-2131:

Github user thvasilo commented on the issue:

    Sure @sachingoel0101 feel free to split up the PRs to reduce overhead.
    For added initialization schemes let me throw [this recent NIPS](https://papers.nips.cc/paper/6478-fast-and-provably-good-seedings-for-k-means)
paper in there, as it might be relatively easy to implement, but we can add it on later as

> Add Initialization schemes for K-means clustering
> -------------------------------------------------
>                 Key: FLINK-2131
>                 URL: https://issues.apache.org/jira/browse/FLINK-2131
>             Project: Flink
>          Issue Type: Task
>          Components: Machine Learning Library
>            Reporter: Sachin Goel
>            Assignee: Sachin Goel
> The Lloyd's [KMeans] algorithm takes initial centroids as its input. However, in case
the user doesn't provide the initial centers, they may ask for a particular initialization
scheme to be followed. The most commonly used are these:
> 1. Random initialization: Self-explanatory
> 2. kmeans++ initialization: http://ilpubs.stanford.edu:8090/778/1/2006-13.pdf
> 3. kmeans|| : http://theory.stanford.edu/~sergei/papers/vldb12-kmpar.pdf
> For very large data sets, or for large values of k, the kmeans|| method is preferred
as it provides the same approximation guarantees as kmeans++ and requires lesser number of
passes over the input data.

This message was sent by Atlassian JIRA

View raw message