Regularization in ResNet with Stochastic DepthDownload PDF

Published: 09 Nov 2021, Last Modified: 05 May 2023NeurIPS 2021 PosterReaders: Everyone
Keywords: ResNet, Stochastic Depth, Regularization, Theory
TL;DR: Stochastic Depth induces regularization via different mechanisms
Abstract: 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.
Supplementary Material: zip
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: zip
13 Replies