English
Related papers

Related papers: The Implicit Bias of Batch Normalization in Linear…

200 papers

A critically important, ubiquitous, and yet poorly understood ingredient in modern deep networks (DNs) is batch normalization (BN), which centers and normalizes the feature maps. To date, only limited progress has been made understanding…

Machine Learning · Computer Science 2022-09-30 Randall Balestriero , Richard G. Baraniuk

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Martin Kolarik , Radim Burget , Kamil Riha

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions…

Machine Learning · Computer Science 2026-05-26 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh

While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics…

Machine Learning · Statistics 2016-07-13 Devansh Arpit , Yingbo Zhou , Bhargava U. Kota , Venu Govindaraju

Batch Whitening is a technique that accelerates and stabilizes training by transforming input features to have a zero mean (Centering) and a unit variance (Scaling), and by removing linear correlation between channels (Decorrelation). In…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yooshin Cho , Hanbyel Cho , Youngsoo Kim , Junmo Kim

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 BatchNorm is to avoid…

Machine Learning · Computer Science 2020-04-30 Eyyüb Sari , Mouloud Belbahri , Vahid Partovi Nia

We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models. We further demonstrate that this finding allows us to make meaningful estimates of the model uncertainty using…

Machine Learning · Statistics 2018-07-17 Mattias Teye , Hossein Azizpour , Kevin Smith

One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize…

Machine Learning · Computer Science 2025-08-14 Jingwei Li , Jing Xu , Zifan Wang , Huishuai Zhang , Jingzhao Zhang

Deep learning opacity often impedes deployment in high-stakes domains. We propose a training framework that aligns model focus with class-representative features without requiring pixel-level annotations. To this end, we introduce…

Artificial Intelligence · Computer Science 2026-02-16 Giacomo Ignesti , Davide Moroni , Massimo Martinelli

A deep equilibrium model uses implicit layers, which are implicitly defined through an equilibrium point of an infinite sequence of computation. It avoids any explicit computation of the infinite sequence by finding an equilibrium point…

Machine Learning · Computer Science 2021-02-19 Kenji Kawaguchi

Batch Normalization is an important approach to advancing deep learning since it allows multiple networks to train simultaneously. A problem arises when normalizing along the batch dimension because B.N.'s error increases significantly as…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Gousia Habib , Ishfaq Ahmed Malik , Jameel Ahmad , Imtiaz Ahmed , Shaima Qureshi

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with the square loss, it…

Machine Learning · Computer Science 2022-06-14 Sangmin Lee , Byeongsu Sim , Jong Chul Ye

Linear programming has played a crucial role in shaping decision-making, resource allocation, and cost reduction in various domains. In this paper, we investigate the application of overparametrized neural networks and their implicit bias…

Optimization and Control · Mathematics 2023-10-05 Haoyue Wang , Promit Ghosal , Rahul Mazumder

Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in…

Computer Vision and Pattern Recognition · Computer Science 2021-02-12 Andrew Brock , Soham De , Samuel L. Smith , Karen Simonyan

Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minimizing the norm of the weight matrices under margin…

Machine Learning · Computer Science 2021-07-22 Andrzej Banburski , Fernanda De La Torre , Nishka Pant , Ishana Shastri , Tomaso Poggio

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

Machine Learning · Computer Science 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Batch Normalization (BatchNorm) is an extremely useful component of modern neural network architectures, enabling optimization using higher learning rates and achieving faster convergence. In this paper, we use mean-field theory to…

Machine Learning · Computer Science 2019-03-08 Mingwei Wei , James Stokes , David J Schwab

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz