criterion = MarginCriterion()

Creates a criterion that optimizes a two-class classification hinge loss (margin-based loss) between input x (a Tensor of dimension 1) and output y (which is a scalar, either 1 or -1) : 

loss(x,y) = forward(x,y) = max(0,m- y x).

m is the margin, which is by default 1. 

criterion = MarginCriterion(marginValue)

sets a different value of m.

Example: 

require "nn"
require "lab"

function gradUpdate(mlp, x, y, criterion, learningRate)
  local pred = mlp:forward(x)
  local err = criterion:forward(pred, y)
  local gradCriterion = criterion:backward(pred, y)
  mlp:zeroGradParameters()
  mlp:backward(x, gradCriterion)
  mlp:updateParameters(learningRate)
end

mlp=nn.Sequential()
mlp:add(nn.Linear(5,1))

x1=lab.rand(5)
x2=lab.rand(5)
criterion=nn.MarginCriterion(1)

for i=1,1000 do
    gradUpdate(mlp,x1,1,criterion,0.01)
    gradUpdate(mlp,x2,-1,criterion,0.01)
end

print(mlp:forward(x1))
print(mlp:forward(x2))

print(criterion:forward(mlp:forward(x1),1))
print(criterion:forward(mlp:forward(x2),-1))
gives the output: 
 1.0043
[torch.Tensor of dimension 1]


-1.0061
[torch.Tensor of dimension 1]

0
0
i.e. the mlp successfully separates the two data points such that they both have a margin of 1, and hence a loss of 0.