Ruocheng Guo

Can I create a variable shared by forward and back propagation in customop('numpy')?

1

I do not quite understand the mechanism behind @customop('numpy'). I find that there's an intermediate variable 'Q' which is expensive to compute and appears in computing both the output and...

Hi, I just find there is an issue in the following function ``` def ndcg(y_pred, y_true, top): assert y_pred.shape[0] == y_true.shape[0] top = min(top, y_pred.shape[0]) first_k_docs = sorted(zip(y_true, y_pred), key=cmp_to_key(doc_comparator))...

Hi, Could you also share the code for the baselines? Best, RC

https://github.com/ilkhem/icebeem/blob/0077f0120c83bcc6d9b199b831485c42bed2401f/models/ivae/ivae_core.py#L255 It seems this part was not mentioned in the AISTATS'20 paper, is this trick important in terms of performance? could you briefly clarify what this part does?