[
https://issues.apache.org/jira/browse/FLINK-1994?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15012510#comment-15012510
]
Trevor Grant commented on FLINK-1994:
-------------------------------------
A little git necromancy here. This issue is done and works more or less as
expected with 5 new gain calculations schemes (the two proposed and 3 I lifted
from sklearn).
This is my first code commit and I need a little guidance. I can add to the
docs/website no problem. The testing suite I'm less sure of. I've never
written useful integration or unit tests before. There is one new parameter
which can take the values 0 through 5. Just would like a little mentoring
before I go mucking up the current test.
The question is: should I create a pull request now, or do I need to complete
the docs AND testing sections before creating the pull request.
Thanks in advance....
tg
> Add different gain calculation schemes to SGD
> ---------------------------------------------
>
> Key: FLINK-1994
> URL: https://issues.apache.org/jira/browse/FLINK-1994
> Project: Flink
> Issue Type: Improvement
> Components: Machine Learning Library
> Reporter: Till Rohrmann
> Assignee: Trevor Grant
> Priority: Minor
> Labels: ML, Starter
>
> The current SGD implementation uses as gain for the weight updates the
> formula {{stepsize/sqrt(iterationNumber)}}. It would be good to make the gain
> calculation configurable and to provide different strategies for that. For
> example:
> * stepsize/(1 + iterationNumber)
> * stepsize*(1 + regularization * stepsize * iterationNumber)^(-3/4)
> See also how to properly select the gains [1].
> Resources:
> [1] http://arxiv.org/pdf/1107.2490.pdf
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
