Generalized Batch Normalization: Towards Accelerating Deep Neural Networks
arXiv:1812.03271
Abstract
Utilizing recently introduced concepts from statistics and quantitative risk management, we present a general variant of Batch Normalization (BN) that offers accelerated convergence of Neural Network training compared to conventional BN. In general, we show that mean and standard deviation are not always the most appropriate choice for the centering and scaling procedure within the BN transformation, particularly if ReLU follows the normalization step. We present a Generalized Batch Normalization (GBN) transformation, which can utilize a variety of alternative deviation measures for scaling and statistics for centering, choices which naturally arise from the theory of generalized deviation measures and risk theory in general. When used in conjunction with the ReLU non-linearity, the underlying risk theory suggests natural, arguably optimal choices for the deviation measure and statistic. Utilizing the suggested deviation measure and statistic, we show experimentally that training is accelerated more so than with conventional BN, often with improved error rate as well. Overall, we propose a more flexible BN transformation supported by a complimentary theoretical framework that can potentially guide design choices.
arXiv commentaccepted at AAAI-19
References in corpus (7)
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Self-Normalizing Neural Networks
- Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
- All you need is a good init
- Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits
- Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks