[GitHub] ZiyueHuang opened a new issue #9528: wrong gradient factor in regression operator

[GitBox <gi...@apache.org>]

ZiyueHuang opened a new issue #9528: wrong gradient factor in regression operator
URL: https://github.com/apache/incubator-mxnet/issues/9528
 
 
   Note: Providing complete information in the most concise form is the best way to get help. This issue template serves as the checklist for essential information to most of the technical issues and bug reports. For non-technical issues and feature requests, feel free to present the information in what you believe is the best form.
   
   For Q & A and discussion, please start a discussion thread at https://discuss.mxnet.io 
   
   ## Description
   Is the gradient factor correct in regression operators(such as `LinearRegressionOutput`)? https://github.com/apache/incubator-mxnet/blob/master/src/operator/regression_output-inl.h#L89-L90
   
   Strictly speaking, `num_output` makes no sense since we don't know the layout of the label.
   
   Even if with the common layout, batch_size first, the implementation is not consistent with the documents,
   
   > By default, gradients of this loss function are scaled by factor 1/n, where n is the number of training examples. The parameter grad_scale can be used to change this scale to grad_scale/n.
   
   `num_output` is indeed the number of dimensions, not the number of training examples.
   
   cc @eric-haibin-lin 
   
   ## Environment info (Required)
   
   ```
   What to do:
   1. Download the diagnosis script from https://raw.githubusercontent.com/apache/incubator-mxnet/master/tools/diagnose.py
   2. Run the script using `python diagnose.py` and paste its output here.
   
   ```
   
   Package used (Python/R/Scala/Julia):
   (I'm using ...)
   
   For Scala user, please provide:
   1. Java version: (`java -version`)
   2. Maven version: (`mvn -version`)
   3. Scala runtime if applicable: (`scala -version`)
   
   For R user, please provide R `sessionInfo()`:
   
   ## Build info (Required if built from source)
   
   Compiler (gcc/clang/mingw/visual studio):
   
   MXNet commit hash:
   (Paste the output of `git rev-parse HEAD` here.)
   
   Build config:
   (Paste the content of config.mk, or the build command.)
   
   ## Error Message:
   (Paste the complete error message, including stack trace.)
   
   ## Minimum reproducible example
   (If you are using your own code, please provide a short script that reproduces the error. Otherwise, please provide link to the existing example.)
   
   ## Steps to reproduce
   (Paste the commands you ran that produced the error.)
   
   1.
   2.
   
   ## What have you tried to solve it?
   
   1.
   2.
   

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services