Skip to content
ml-recall

#loss-reduction

1 question from PyTorch

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedPyTorch

Training with nn.MSELoss() (the default reduction='mean') and torch.optim.SGD with lr=0.03 works well on minibatches of 64 examples. You switch to nn.MSELoss(reduction='sum'). Which learning rate gives exactly the same parameter updates?

a number, e.g. 0.0012