Do deep nets really need weight decay and dropout?

Alex Hernández-García, Peter König

Feb 12, 2018 (modified: Jun 04, 2018) ICLR 2018 Workshop Submission readers: everyone Show Bibtex
  • Abstract: The impressive success of modern deep neural networks on computer vision tasks has been achieved through models of very large capacity compared to the number of available training examples. This overparameterization is often said to be controlled with the help of different regularization techniques, mainly weight decay and dropout. However, since these techniques reduce the effective capacity of the model, typically even deeper and wider architectures are required to compensate for the reduced capacity. Therefore, there seems to be a waste of capacity in this practice. In this paper we build upon recent research that suggests that explicit regularization may not be as important as widely believed and carry out an ablation study that concludes that weight decay and dropout may not be necessary for object recognition if enough data augmentation is introduced.
  • Keywords: convolutional neural networks, regularization, data augmentation
  • TL;DR: Weight decay and dropout regularization might benot only unnecessary, but their generalization gains can be achieved by data augmentation alone.