[jira] [Commented] (FLINK-1994) Add different gain calculation schemes to SGD

["Trevor Grant (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/FLINK-1994?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14701200#comment-14701200 ] 

Trevor Grant commented on FLINK-1994:
-------------------------------------

I more or less have this working with a few new optimizers based on sklearn- specifically the constant, optimal, and inverse scaling. 
Reading this paper to find others, as well as including bulleted ones in issue.

> 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)