How Does Batch Normalization Help Optimization?
Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reasons for BatchNorm's effectiveness are still poorly understood. The popular belief is that this effectiveness stems from controlling the change of the layers' input distributions during training to reduce the so-called "internal covariate shift". In this work, we demonstrate that such distributional stability of layer inputs has little to do with the success of BatchNorm. Instead, we uncover a more fundamental impact of BatchNorm on the training process: it makes the optimization landscape significantly smoother. This smoothness induces a more predictive and stable behavior of the gradients, allowing for faster training.
Code (10)
Similar Papers 제목 키워드 기반
Batch normalization does not improve initialization
Batch normalization is one of the most important regularization techniques for neural networks, significantly improving training by centering the layers of the neural network. There have been several attempts to provide …
How Does Batch Normalization Help Binary Training?
Binary Neural Networks (BNNs) are difficult to train, and suffer from drop of accuracy. It appears in practice that BNNs fail to train in the absence of Batch Normalization (BatchNorm) layer. We find the main role of Bat…
QuantizationBatch Normalized Recurrent Neural Networks
Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent …
Language Modellingspeech-recognitionSpeech RecognitionRevisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization
Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on how the batches are constructed during tra…
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we impro…
Deep Reinforcement LearningImage Classificationreinforcement-learningReinforcement Learning+1