Stable ResNet
This addresses stability and expressivity problems in deep neural networks for researchers and practitioners in machine learning, representing an incremental improvement over existing ResNet variants.
The paper tackles the issues of gradient exploding and loss of expressivity in deep ResNet architectures by introducing Stable ResNet, which stabilizes gradients and maintains expressivity in the infinite depth limit.
Deep ResNet architectures have achieved state of the art performance on many tasks. While they solve the problem of gradient vanishing, they might suffer from gradient exploding as the depth becomes large (Yang et al. 2017). Moreover, recent results have shown that ResNet might lose expressivity as the depth goes to infinity (Yang et al. 2017, Hayou et al. 2019). To resolve these issues, we introduce a new class of ResNet architectures, called Stable ResNet, that have the property of stabilizing the gradient while ensuring expressivity in the infinite depth limit.