formath commented on issue #7942: Adam optimizer consistent with paper URL: https://github.com/apache/incubator-mxnet/pull/7942#issuecomment-331061537 In my use, namely training `field aware factorization machine` on 20 millions features and billions instances, setting `rho` 0.999 really works. It could get an absolute 0.01 promotion on AUC. I don't know whether it works on cv or nlp tasks but giving user a chance could be useful. @sxjscience ---------------------------------------------------------------- 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
