by Daniel Pollithy

This is a short note to show the difference between softmax and softargmax.

It is common to use a “Softmax” layer as an activation function for a neural network used for classification. But this is actually a wrong name. The layer should be called softargmax.


Given a vector x = [20, 5, 0.1, 300]. The softmax (also called LogSumExp) is a approximation to the maximum of the vector. Let’s apply the three steps in the name:

  1. exp: exp([20, 5, 0.1, 300]) -> [4.8e+008, 1.4e+002, 1.1e+000, 1.9e+130]
  2. sum: ~1.9e+130
  3. log: 299.97

Note: If there were two “300” in the input vector, then the sum in the second step was 2 * 1.9e+130. Third step: log(2 * 1.9e+130) = log(2) + log(1.9e+130) = 300.67


The softargmax divides each entry of the input vector x by the softmax. Therefore it can be seen as a probability measure. The probability of each entry to be the maximum of the vector.

  1. Calculate softmax s=299.97
  2. x’ = x/s = [20, 5, 0.1, 300] / 299.97 ~= [0.066, 0.016, 0.0003, 1.0001]

In the classification framework we would choose the fourth class as a prediction.


  1. Maximum rewritten:
  2. Softargmax definition:
  3. Upper bound for Softargmax:
  4. Factor out n:
  5. Log rule:
  6. Insert defintion of max:
  7. Result: