Returns the unmodified loss value
Returns the unmodified loss value
The updated loss is oldLoss
The loss to be updated
The weights used to update the loss
The regularization parameter which is ignored
Updated loss
Calculates the new weights based on the gradient
Calculates the new weights based on the gradient
The updated weight is w - learningRate *gradient
where w
is the weight vector
The weights to be updated
The gradient according to which we will update the weights
The regularization parameter which is ignored
The effective step size for this iteration
Updated weights
No regularization penalty.