Training Instability and Disharmony Between ReLU and Batch Normalization

Inyoung Paik, Jaesik Choi

Keywords: Deep learning, Gradient Exploding, ReLU, Batch normalization, Training instability, LARS, WarmUp

TL;DR: We mathematically show how the disharmony between ReLU and BN causes temporal gradient explosion and training instability. We also propose a better solution of the problem.

Abstract: Deep neural networks based on batch normalization and ReLU-like activation functions experience instability during early stages of training owing to the high gradient induced by temporal gradient explosion. ReLU reduces the variance by more than the expected amount and batch normalization amplifies the gradient during its recovery. In this paper, we explain the explosion of a gradient mathematically while the forward propagation remains stable, and also the alleviation of the problem during training. Based on this, we propose a Layer-wise Asymmetric Learning rate Clipping (LALC) algorithm, which outperforms existing learning rate scaling methods in large batch training and can also be used to replace WarmUp in small batch training.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning