Model partial derivatives into loss function

autograd
1

I want to force a monotonic relationship between a set of features and the model’s outcome, and I would like to do it by controlling the model’s partial derivatives into the loss function, like a regularization term.

I tried the solution proposed here, but I got an error:

one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [2, 1]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

Is there a way to include the model’s partial derivatives into the loss?

2

Hi,

This is the same error as the one from the post you linked. Does the answer there help you?

3

Hi Alban,

I tried the solution proposed (simply copy pasting) but is not working.