eric-haibin-lin opened a new issue #9881: Inconsistent weight decay logics in multiple optimizers URL: https://github.com/apache/incubator-mxnet/issues/9881 ### wd applied before clip_gradient by the optimizer - RMSProp - Adamax - Nadam - FTML ### wd applied after clip_gradient by the optimizer - SGD - Signum - LBSGD - DCASGD - NAG - SGLD - Adam ### wd applied after clip_gradient by the optimizer, and not used to update to states - AdaDelta - AdaGrad - Ftrl
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services