Saeed Ahmad

icon indicating a website link https://saeedahmad.me

icon company Korea National University of Transportation icon location North Chungcheong, South Korea icon location Research Assistant @ KNUT | Machine Learning Engineer

Results 3 comments of Saeed Ahmad

optimizer.zero_grad() before loss.backward()?

When we start your training loop, ideally we should [zero out the gradients](https://pytorch.org/docs/stable/optim.html#torch.optim.Optimizer.zero_grad) so that we do the parameter update correctly. Otherwise, the gradient would be a combination of the...

[REVIEW]: Pycausal-Explorer: A Scikit-learn compatible causal inference toolkit

## Review checklist for @saeedahmadicp ### Conflict of interest - [x] I confirm that I have read the [JOSS conflict of interest (COI) policy](https://github.com/openjournals/joss/blob/master/COI.md) and that: I have no COIs...

[REVIEW]: Pycausal-Explorer: A Scikit-learn compatible causal inference toolkit

Dear @teonbrooks, I have carefully reviewed the submission you sent. The article and the accompanying package aim to provide a Python module for causal inference and treatment effect estimation. While...