Complexity control by gradient descent in deep networks
Tomaso Poggio, Qianli Liao, Andrzej Banburski · Nature Communications · 2020
Overparametrized deep networks predict well, despite the lack of an explicit complexity control during training, such as an explicit regularization term. For exponential-type loss functions, we solve this puzzle by showing an effective regularization effect of gradient descent in terms of the normalized weights that are relevant for classification.