Regularization in ResNet with Stochastic Depth
This work addresses a theoretical gap for researchers using Stochastic Depth in deep learning, but it is incremental as it builds on existing empirical successes.
The paper tackled the lack of theoretical understanding of Stochastic Depth regularization in ResNets by providing a hybrid analysis combining perturbation analysis and signal propagation, resulting in principled guidelines for choosing survival rates.
Regularization plays a major role in modern deep learning. From classic techniques such as L1,L2 penalties to other noise-based methods such as Dropout, regularization often yields better generalization properties by avoiding overfitting. Recently, Stochastic Depth (SD) has emerged as an alternative regularization technique for residual neural networks (ResNets) and has proven to boost the performance of ResNet on many tasks [Huang et al., 2016]. Despite the recent success of SD, little is known about this technique from a theoretical perspective. This paper provides a hybrid analysis combining perturbation analysis and signal propagation to shed light on different regularization effects of SD. Our analysis allows us to derive principled guidelines for choosing the survival rates used for training with SD.