[
https://issues.apache.org/jira/browse/FLINK-1807?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14526616#comment-14526616
]
ASF GitHub Bot commented on FLINK-1807:
---------------------------------------
Github user tillrohrmann commented on the pull request:
https://github.com/apache/flink/pull/613#issuecomment-98702926
The refactoring looks really good @thvasilo. I had only two comments:
1. Why do we limit the optimization framework to linear models?
2. Why do we calculate the regularization gradient for each data point in
the gradient calculation phase and not in the weight update step?
> Stochastic gradient descent optimizer for ML library
> ----------------------------------------------------
>
> Key: FLINK-1807
> URL: https://issues.apache.org/jira/browse/FLINK-1807
> Project: Flink
> Issue Type: Improvement
> Components: Machine Learning Library
> Reporter: Till Rohrmann
> Assignee: Theodore Vasiloudis
> Labels: ML
>
> Stochastic gradient descent (SGD) is a widely used optimization technique in
> different ML algorithms. Thus, it would be helpful to provide a generalized
> SGD implementation which can be instantiated with the respective gradient
> computation. Such a building block would make the development of future
> algorithms easier.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
