English
Related papers

Related papers: Understanding Decoupled and Early Weight Decay

200 papers

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a…

Machine Learning · Computer Science 2026-05-01 Aditya A. Ramesh , Alex Lewandowski , Jürgen Schmidhuber

Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization and…

Machine Learning · Computer Science 2019-09-27 Kaichao You , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Applying weight decay (WD) to matrix layers is standard practice in large-language-model pretraining. Prior work suggests that stochastic gradient noise induces a Brownian-like expansion of the weight matrices W, whose growth is…

Machine Learning · Computer Science 2026-01-09 Maksim Velikanov , Ilyas Chahed , Jingwei Zuo , Dhia Eddine Rhaiem , Younes Belkada , Hakim Hacid

We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parameter on the fly based…

Machine Learning · Computer Science 2023-12-05 Amin Ghiasi , Ali Shafahi , Reza Ardekani

We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that uses the distance the weights have moved from their initial…

Machine Learning · Statistics 2021-01-18 Henry Gouk , Timothy M. Hospedales , Massimiliano Pontil

To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Tao Li , Weihao Yan , Zehao Lei , Yingwen Wu , Kun Fang , Ming Yang , Xiaolin Huang

Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this…

Machine Learning · Computer Science 2017-02-21 David P. Helmbold , Philip M. Long

Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved…

Machine Learning · Computer Science 2024-11-22 Denis Tarasov , Anja Surina , Caglar Gulcehre

Lagrangian decomposition (LD) is a relaxation method that provides a dual bound for constrained optimization problems by decomposing them into more manageable sub-problems. This bound can be used in branch-and-bound algorithms to prune the…

Artificial Intelligence · Computer Science 2024-08-26 Swann Bessa , Darius Dabert , Max Bourgeat , Louis-Martin Rousseau , Quentin Cappart

Averaging iterations of Stochastic Gradient Descent (SGD) have achieved empirical success in training deep learning models, such as Stochastic Weight Averaging (SWA), Exponential Moving Average (EMA), and LAtest Weight Averaging (LAWA).…

Machine Learning · Computer Science 2024-11-21 Peng Wang , Li Shen , Zerui Tao , Yan Sun , Guodong Zheng , Dacheng Tao

The growing interest in satellite imagery has triggered the need for efficient mechanisms to extract valuable information from these vast data sources, providing deeper insights. Even though deep learning has shown significant progress in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Wadii Boulila , Eman Alshanqiti , Ayyub Alzahem , Anis Koubaa , Nabil Mlaiki

We analyze the inductive bias of gradient descent for weight normalized smooth homogeneous neural nets, when trained on exponential or cross-entropy loss. We analyse both standard weight normalization (SWN) and exponential weight…

Machine Learning · Computer Science 2023-02-02 Depen Morwani , Harish G. Ramaswamy

With the accumulation of resources in the era of big data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Xin Ning , Qiankun Li , Xiaolong Huang , Qiupu Chen , Feng He , Weijun Li , Prayag Tiwari , Xinwang Liu

In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with…

Machine Learning · Computer Science 2018-03-01 Robert Kwiatkowski , Oscar Chang

Training neural networks with batch normalization and weight decay has become a common practice in recent years. In this work, we show that their combined use may result in a surprising periodic behavior of optimization dynamics: the…

Machine Learning · Computer Science 2022-01-19 Ekaterina Lobacheva , Maxim Kodryan , Nadezhda Chirkova , Andrey Malinin , Dmitry Vetrov

Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization…

Machine Learning · Computer Science 2019-11-07 Pavel Sulimov , Elena Sukmanova , Roman Chereshnev , Attila Kertesz-Farkas

In modern deep learning, weight decay is often credited with "stabilizing" training dynamics, diverging from its classical role as a static regularization penalty. We investigate a fundamental question: *does weight decay stabilize training…

Machine Learning · Computer Science 2026-05-19 Marius Saether , Amir Kolic , Tomaso Poggio , Pierfrancesco Beneventano

Weight play an essential role in deep learning network models. Unlike network structure design, this article proposes the concept of weight augmentation, focusing on weight exploration. The core of Weight Augmentation Strategy (WAS) is to…

Machine Learning · Computer Science 2024-05-31 Junbin Zhuang , Guiguang Din , Yunyi Yan

To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Can Peng , Kun Zhao , Sam Maksoud , Tianren Wang , Brian C. Lovell
‹ Prev 1 3 4 5 6 7 10 Next ›