criterion = L1HingeEmbeddingCriterion(margin)

Creates a criterion that measures the loss given an input x = {x1,x2}, a table of two tensors, and a label y (1 or -1): This is used for measuring whether two inputs are similar or dissimilar, using the L1 distance, and is typically used for learning nonlinear embeddings or semi-supervised learning. 

loss(x,y) = forward(x,y) = ||x1-x2||_1, if y=1
                         = max(0,margin - ||x1-x2||_1), if y=-1

The margin has a default value of 1, or can be set in the constructor: 

criterion = L1HingeEmbeddingCriterion(marginValue)