Complexity control by gradient descent in deep networks
© 2020, The Author(s). 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...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer Science and Business Media LLC
2021
|
Online Access: | https://hdl.handle.net/1721.1/136301 |
Summary: | © 2020, The Author(s). 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. |
---|