# Should L2 regularization be corrected for scale?

I am training a deep neural network using cross entropy loss and L2 regularization, so the final cost function looks something like this: $$E = - \frac{1}{N_{samples}} \sum_{i=1}^{N_{samples}} \text{cross_entropy}\left(x_i, y_i\right) + \lambda \sum_{j=1}^{N_{layers}}\sum_{k=1}^{N_{units}^j}\sum_{l=1}^{N_{units}^{j+1}} \left(w^j_{k,l}\right)^2$$ where the first term is the cross entropy over classes (averaged over the size of the training set) and the second term is the sum of squared weights involved in the network ($w^j_{k,l}$ is the weight from $k$-th unit in $j$-th layer to $l$-th unit in $(j+1)$-th layer), and $\lambda$ is a regularization strength parameter.

My question is: won't the number of layers and units affect the scale of the regularization term ? Therefore, wouldn't it make more sense to normalize the second term by the number of weights (i.e., replacing $\frac{\lambda}{N_{layers}N^j_{units}N^{j+1}_{units}}$ for $\lambda$).

Unfortunately, I've not found any reference about this. I've just found in Bengio's paper  (weight decay subsection) that they recommend to scale according to the number of mini-batches in each epoch (which I do not really see the reason why).

 Practical Recommendations for Gradient-Based Training of Deep Architectures

In his paper I don't think he is normalizing loss by n samples as you are doing: 