English
Related papers

Related papers: Batch Normalization Orthogonalizes Representations…

200 papers

Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typically has only 1-2 images for training, which is inevitable for…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Siyuan Qiao , Huiyu Wang , Chenxi Liu , Wei Shen , Alan Yuille

Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks…

Machine Learning · Computer Science 2026-05-04 Xuan Son Nguyen , Nistor Grozavu

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

The training dynamics of two-layer neural networks with batch normalization (BN) is studied. It is written as the training dynamics of a neural network without BN on a Riemannian manifold. Therefore, we identify BN's effect of changing the…

Machine Learning · Computer Science 2021-10-19 Chao Ma , Lexing Ying

Batch normalization (BN) is a milestone technique in deep learning. It normalizes the activation using mini-batch statistics during training but the estimated population statistics during inference. This paper focuses on investigating the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Lei Huang , Yi Zhou , Tian Wang , Jie Luo , Xianglong Liu

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions by standardizing with…

Machine Learning · Computer Science 2021-05-06 Mandy Lu , Qingyu Zhao , Jiequan Zhang , Kilian M. Pohl , Li Fei-Fei , Juan Carlos Niebles , Ehsan Adeli

Batch normalization dramatically increases the largest trainable depth of residual networks, and this benefit has been crucial to the empirical success of deep residual networks on a wide range of benchmarks. We show that this key benefit…

Machine Learning · Computer Science 2020-12-10 Soham De , Samuel L. Smith

Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by…

Machine Learning · Computer Science 2021-04-07 Lei Huang , Yi Zhou , Li Liu , Fan Zhu , Ling Shao

We take a geometrical viewpoint and present a unifying view on supervised deep learning with the Bregman divergence loss function - this entails frequent classification and prediction tasks. Motivated by simulations we suggest that there is…

Machine Learning · Computer Science 2021-07-07 Petr Taborsky , Lars Kai Hansen

Normalization techniques have been widely used in the field of deep learning due to their capability of enabling higher learning rates and are less careful in initialization. However, the effectiveness of popular normalization technologies…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Afifa Khaled , Chao Li , Jia Ning , Kun He

Deep Neural Networks (DNNs) have begun to thrive in the field of automation systems, owing to the recent advancements in standardising various aspects such as architecture, optimization techniques, and regularization. In this paper, we take…

Machine Learning · Computer Science 2019-07-10 Anand Krishnamoorthy Subramanian , Nak Young Chong

Intriguing empirical evidence exists that deep learning can work well with exoticschedules for varying the learning rate. This paper suggests that the phenomenon may be due to Batch Normalization or BN, which is ubiquitous and provides…

Machine Learning · Computer Science 2019-11-22 Zhiyuan Li , Sanjeev Arora

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

Probability · Mathematics 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

Normalization techniques such as Batch Normalization have been applied successfully for training deep neural networks. Yet, despite its apparent empirical benefits, the reasons behind the success of Batch Normalization are mostly…

Machine Learning · Statistics 2018-10-09 Jonas Kohler , Hadi Daneshmand , Aurelien Lucchi , Ming Zhou , Klaus Neymeyr , Thomas Hofmann

Deep neural networks have been demonstrated to achieve phenomenal success in many domains, and yet their inner mechanisms are not well understood. In this paper, we investigate the curvature of image manifolds, i.e., the manifold deviation…

Machine Learning · Computer Science 2023-11-17 Ilya Kaufman , Omri Azencot

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neural networks, as the number or neurons (ie, the size of the…

Machine Learning · Statistics 2020-07-15 Valentin De Bortoli , Alain Durmus , Xavier Fontaine , Umut Simsekli

Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation…

Machine Learning · Computer Science 2024-06-04 Yunhao Ni , Yuxin Guo , Junlong Jia , Lei Huang

We study the implicit bias of batch normalization trained by gradient descent. We show that when learning a linear model with batch normalization for binary classification, gradient descent converges to a uniform margin classifier on the…

Machine Learning · Computer Science 2023-07-12 Yuan Cao , Difan Zou , Yuanzhi Li , Quanquan Gu

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada