D-Roberts commented on pull request #18197: URL: https://github.com/apache/incubator-mxnet/pull/18197#issuecomment-628641606
The code follows the idea in the reference [Differential Programming Tensor Networks](https://journals.aps.org/prx/pdf/10.1103/PhysRevX.9.031041). At high level, partition/split the input A into 2 matrices X and Y and R (from A=QR decomposition) into 2 matrices U and V. Then X = QU and get X_grad by applying the gradient derivation from the square input case (m=n) with adjusted Q_grad. Also get Y_grad separately. Then A_grad is the concatenation of X_grad and Y_grad. ---------------------------------------------------------------- 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: us...@infra.apache.org