You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@madlib.apache.org by "Rahul Iyer (JIRA)" <ji...@apache.org> on 2018/08/29 17:16:00 UTC

[jira] [Created] (MADLIB-1272) Simplify Nesterov by performing velocity update in previous iteration

Rahul Iyer created MADLIB-1272:
----------------------------------

             Summary: Simplify Nesterov by performing velocity update in previous iteration
                 Key: MADLIB-1272
                 URL: https://issues.apache.org/jira/browse/MADLIB-1272
             Project: Apache MADlib
          Issue Type: Bug
          Components: Module: Neural Networks
            Reporter: Rahul Iyer


Momentum updates are complicated due to Nesterov requiring an initial update before gradient calculations. There is, however, a different form of the Nesterov update that can be cleanly performed after the regular update, simplifying the code. This allows performing the gradient calculations before any update - with or without Nesterov. 

 

 



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)