## Towards Understanding Regularization in Batch Normalization

27 Sept 2018, 22:36 (modified: 10 Feb 2022, 11:31)ICLR 2019 Conference Blind SubmissionReaders: Everyone
Keywords: batch normalization, regularization, deep learning
Abstract: Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a BN layer, and a nonlinear activation function. This basic network helps us understand the impacts of BN in three aspects. First, by viewing BN as an implicit regularizer, BN can be decomposed into population normalization (PN) and gamma decay as an explicit regularization. Second, learning dynamics of BN and the regularization show that training converged with large maximum and effective learning rate. Third, generalization of BN is explored by using statistical mechanics. Experiments demonstrate that BN in convolutional neural networks share the same traits of regularization as the above analyses.
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10)
8 Replies