English
Related papers

Related papers: Decoupled Weight Decay Regularization

200 papers

We consider a decentralized learning setting in which data is distributed over nodes in a graph. The goal is to learn a global model on the distributed data without involving any central entity that needs to be trusted. While gossip-based…

Information Theory · Computer Science 2021-03-17 Ghadir Ayache , Salim El Rouayheb

Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in…

Machine Learning · Statistics 2025-04-08 Ziyang Wei , Wanrong Zhu , Wei Biao Wu

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate…

Machine Learning · Statistics 2020-08-28 Antti Koskela , Antti Honkela

Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well…

Machine Learning · Computer Science 2024-07-18 Kushal Chakrabarti , Mayank Baranwal

We consider the problem of denoising with the help of prior information taken from a database of clean signals or images. Denoising with variational methods is very efficient if a regularizer well adapted to the nature of the data is…

Machine Learning · Computer Science 2023-10-06 Hui Shi , Yann Traonmilin , J-F Aujol

Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to local and even global…

Machine Learning · Computer Science 2025-12-02 Meng Zhu , Quan Xiao , Weidong Min

Weight decay is a broadly used technique for training state-of-the-art deep networks from image classification to large language models. Despite its widespread usage and being extensively studied in the classical literature, its role…

Machine Learning · Computer Science 2024-11-06 Francesco D'Angelo , Maksym Andriushchenko , Aditya Varre , Nicolas Flammarion

Deep neural networks have had an enormous impact on image analysis. State-of-the-art training methods, based on weight decay and DropOut, result in impressive performance when a very large training set is available. However, they tend to…

Machine Learning · Computer Science 2019-09-02 Amal Rannen Triki , Matthew B. Blaschko

Stochastic gradient descent (SGD) is a popular stochastic optimization method in machine learning. Traditional parallel SGD algorithms, e.g., SimuParallel SGD, often require all nodes to have the same performance or to consume equal…

Machine Learning · Computer Science 2017-08-17 Cheng Daning , Li Shigang , Zhang Yunquan

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 improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

Adaptive gradient algorithm (AdaGrad) and its variants, such as RMSProp, Adam, AMSGrad, etc, have been widely used in deep learning. Although these algorithms are faster in the early phase of training, their generalization performance is…

Machine Learning · Computer Science 2021-09-14 Kun Zeng , Jinlan Liu , Zhixia Jiang , Dongpo Xu

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine Learning · Computer Science 2026-05-29 Ruoran Xu , Borong She , Xiaobo Jin , Qiufeng Wang

We study the implicit bias towards low-rank weight matrices when training neural networks (NN) with Weight Decay (WD). We prove that when a ReLU NN is sufficiently trained with Stochastic Gradient Descent (SGD) and WD, its weight matrix is…

Machine Learning · Computer Science 2024-10-04 Ke Chen , Chugang Yi , Haizhao Yang

This paper is devoted to proposing a general weighted low-rank recovery model and designing a fast SVD-free computational scheme to solve it. First, our generic weighted low-rank recovery model unifies several existing approaches in the…

Optimization and Control · Mathematics 2022-08-02 Aritra Dutta , Jingwei Liang , Xin Li

Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout…

Machine Learning · Statistics 2013-11-04 Stefan Wager , Sida Wang , Percy Liang

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many…

The momentum acceleration technique is widely adopted in many optimization algorithms. However, there is no theoretical answer on how the momentum affects the generalization performance of the optimization algorithms. This paper studies…

Machine Learning · Computer Science 2022-05-30 Bohan Wang , Qi Meng , Huishuai Zhang , Ruoyu Sun , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

$L_0$-smoothness, which has been pivotal to advancing decentralized optimization theory, is often fairly restrictive for modern tasks like deep learning. The recent advent of relaxed $(L_0,L_1)$-smoothness condition enables improved…

Optimization and Control · Mathematics 2025-08-13 Zhanhong Jiang , Aditya Balu , Soumik Sarkar

Despite superior training outcomes, adaptive optimization methods such as Adam, Adagrad or RMSprop have been found to generalize poorly compared to Stochastic gradient descent (SGD). These methods tend to perform well in the initial portion…

Machine Learning · Computer Science 2017-12-21 Nitish Shirish Keskar , Richard Socher