eric-haibin-lin commented on issue #17728: Poor performance when we use mx.symbol.Variable(..,..,stype="row-sparse") to define the variable URL: https://github.com/apache/incubator-mxnet/issues/17728#issuecomment-593719010 Yes, if you look at the Adam optimization algorithm, zero grad does not lead to zero update. But SGD and Adagrad does.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
