paper-with-me

Papers

L2 Regularization versus Batch and Weight Normalization

2017-06-16 · Twan van Laarhoven

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization has no regularizing effect when combined with normalization. Instead, regularization has an influence on the scale of weights, and thereby on the effective learning rate. We investigate this dependence, both in theory, and experimentally. We show that popular optimization methods such as ADAM only partially eliminate the influence of normalization on the learning rate. This leads to a discussion on other ways to mitigate this issue.

📄 PDF Abstract BibTeX arXiv:1706.05350

Code (0)

등록된 구현이 없습니다.

Tasks

L2 Regularization

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Four Things Everyone Should Know to Improve Batch Normalization

2019-06-09 · ICLR 2020 1 · Cecilia Summers, Michael J. Dinneen

A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging bot…

Theoretical Insight into Batch Normalization: Data Dependant Auto-Tuning of Regularization Rate

2022-09-15 · Lakshmi Annamalai, Chetan Singh Thakur

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower…

Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification

2017-09-24 · Igor Gitman, Boris Ginsburg

Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is a memory-…

General Classificationimage-classificationImage Classification

Normalization Before Shaking Toward Learning Symmetrically Distributed Representation Without Margin in Speech Emotion Recognition

2018-08-02 · Che-Wei Huang, Shrikanth. S. Narayanan

Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition…

Data AugmentationEmotion RecognitionGeneral ClassificationSpeech Emotion Recognition

A Robust Initialization of Residual Blocks for Effective ResNet Training without Batch Normalization

2021-12-23 · Enrico Civitelli, Alessio Sortino, Matteo Lapucci, Francesco Bagattini 외

Batch Normalization is an essential component of all state-of-the-art neural networks architectures. However, since it introduces many practical issues, much recent research has been devoted to designing normalization-fr…