@article {4433, title = {Complexity Control by Gradient Descent in Deep Networks}, journal = {Nature Communications}, volume = {11}, year = {2020}, month = {02/2020}, abstract = {
Overparametrized deep network 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.
}, doi = {https://doi.org/10.1038/s41467-020-14663-9}, url = {https://www.nature.com/articles/s41467-020-14663-9}, author = {Tomaso Poggio and Qianli Liao and Andrzej Banburski} }