I have a question regarding Tensorflow:
Which loss function is used in tf.nn.sampled_softmax_loss?
I believe it's cross-entropy, but it is not written on the official website. Can anyone confirm my guess?
Based on this other question, it looks like it is cross entropy.
Besides, the main difference between sampled_softmax_loss and softmax_cross_entropy_with_logits (the standard cross_entropy loss in TF) is that the first only takes into account a subset V of your vocabulary to calculate your loss, while the second takes into account your entire vocabulary.