[ https://issues.apache.org/jira/browse/FLINK-1994?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15026966#comment-15026966 ]
ASF GitHub Bot commented on FLINK-1994: --------------------------------------- Github user StephanEwen commented on the pull request: https://github.com/apache/flink/pull/1397#issuecomment-159648629 The Kafka tests are not written in a bullet proof way. It may happen that the Kafka test-cluster has a hickup, in which case the tests cannot succeed... You can (force) push changes to your branch, that re-triggers the CI. > 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)