Compute the gradient of the SVM loss function

Tags: , , ,

I am trying to implement the SVM loss function and its gradient. I found some example projects that implement these two, but I could not figure out how they can use the loss function when computing the gradient.

Here is the formula of loss function: enter image description here

What I cannot understand is that how can I use the loss function’s result while computing gradient?

The example project computes the gradient as follows:

for i in xrange(num_train):
    scores = X[i].dot(W)
    correct_class_score = scores[y[i]]
    for j in xrange(num_classes):
      if j == y[i]:
      margin = scores[j] - correct_class_score + 1 # note delta = 1
      if margin > 0:
        loss += margin
        dW[:,j] += X[i]
        dW[:,y[i]] -= X[i] 

dW is for gradient result. And X is the array of training data. But I didn’t understand how the derivative of the loss function results in this code.


The method to calculate gradient in this case is Calculus (analytically, NOT numerically!). So we differentiate loss function with respect to W(yi) like this: enter image description here

and with respect to W(j) when j!=yi is:

enter image description here

The 1 is just indicator function so we can ignore the middle form when condition is true. And when you write in code, the example you provided is the answer.

Since you are using cs231n example, you should definitely check note and videos if needed.

Hope this helps!

Source: stackoverflow