My question is I'm thinking is there any reason we can simplify cross entropy loss into the below way instead of what [1] used in cross-entropy.
def pointwise_loss(positive_predictions, negative_predictions, mask=None):
"""
Logistic loss function.
Parameters
----------
positive_predictions: tensor
Tensor containing predictions for known positive items.
negative_predictions: tensor
Tensor containing predictions for sampled negative items.
mask: tensor, optional
A binary tensor used to zero the loss from some entries
of the loss tensor.
Returns
-------
loss, float
The mean value of the loss function.
"""
positives_loss = (1.0 - torch.sigmoid(positive_predictions))
negatives_loss = torch.sigmoid(negative_predictions)
loss = (positives_loss + negatives_loss)
if mask is not None:
mask = mask.float()
loss = loss * mask
return loss.sum() / mask.sum()
return loss.mean()
My question is I'm thinking is there any reason we can simplify cross entropy loss into the below way instead of what [1] used in cross-entropy.
[1].https://ml-cheatsheet.readthedocs.io/en/latest/logistic_regression.html