English
Related papers

Related papers: Decoupled Weight Decay Regularization

200 papers

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

Within the context of intelligent manufacturing, industrial robots have a pivotal function. Nonetheless, extended operational periods cause a decline in their absolute positioning accuracy, preventing them from meeting high precision. To…

Robotics · Computer Science 2024-08-23 Tinghui Chen , Shuai Li

This paper investigates the stochastic optimization problem with a focus on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural…

Machine Learning · Computer Science 2020-04-09 Pengzhan Guo , Zeyang Ye , Keli Xiao , Wei Zhu

Much of the existing theory on first-order non-smooth optimization is built on a restrictive assumption that the gradients of the objective function are uniformly bounded. We introduce a much more realistic class of generalized Lipschitz…

Optimization and Control · Mathematics 2026-05-27 Dmitry Kovalev

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant…

Machine Learning · Computer Science 2020-01-24 Jiyang Bai , Yuxiang Ren , Jiawei Zhang

Adam has been widely adopted for training deep neural networks due to less hyperparameter tuning and remarkable performance. To improve generalization, Adam is typically used in tandem with a squared $\ell_2$ regularizer (referred to as…

Machine Learning · Computer Science 2022-02-02 Zhenxun Zhuang , Mingrui Liu , Ashok Cutkosky , Francesco Orabona

It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large Language Models (LLMs). Yet the underlying reason for this gap remains unclear. In this…

Machine Learning · Computer Science 2026-05-19 Athanasios Glentis , Dawei Li , Chung-Yiu Yau , Mingyi Hong

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

We introduce Cautious Weight Decay (CWD), a one-line, optimizer-agnostic modification that applies weight decay only to parameter coordinates whose signs align with the optimizer update. Unlike standard decoupled decay, which implicitly…

Machine Learning · Computer Science 2026-02-25 Lizhang Chen , Jonathan Li , Kaizhao Liang , Baiyu Su , Cong Xie , Nuo Wang Pierse , Chen Liang , Ni Lao , Qiang Liu

Adaptive optimizers such as Adam (Kingma & Ba, 2015) have been central to the success of large language models. However, they often require to maintain optimizer states throughout training, which can result in memory requirements several…

Machine Learning · Computer Science 2025-02-24 Chao Ma , Wenbo Gong , Meyer Scetbon , Edward Meeds

Deep learning methods - usually consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays omnipresent in data-driven learning problems as well as in scientific…

Optimization and Control · Mathematics 2025-01-13 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its…

Machine Learning · Computer Science 2024-02-13 Anuraganand Sharma

Adaptive methods like Adam have become the $\textit{de facto}$ standard for large-scale vector and Euclidean optimization due to their coordinate-wise adaptation with a second-order nature. More recently, matrix-based spectral optimizers…

Machine Learning · Computer Science 2026-05-28 Zitao Song , Cedar Site Bai , Zhe Zhang , Brian Bullins , David F. Gleich

Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Adam rely on the bounded smoothness assumption, referred to as…

Machine Learning · Computer Science 2024-06-25 Bohan Wang , Yushun Zhang , Huishuai Zhang , Qi Meng , Ruoyu Sun , Zhi-Ming Ma , Tie-Yan Liu , Zhi-Quan Luo , Wei Chen

We prove local convergence of several notable gradient descent algorithms used in machine learning, for which standard stochastic gradient descent theory does not apply directly. This includes, first, online algorithms for recurrent models…

Dynamical Systems · Mathematics 2021-01-11 Pierre-Yves Massé , Yann Ollivier

In this work, we propose an optimization algorithm which we call norm-adapted gradient descent. This algorithm is similar to other gradient-based optimization algorithms like Adam or Adagrad in that it adapts the learning rate of stochastic…

Machine Learning · Computer Science 2020-10-14 David Sprunger

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by…

Machine Learning · Computer Science 2018-12-03 Michal Rolinek , Georg Martius

Sharpness-Aware Minimization (SAM) improves model generalization but doubles the computational cost of Stochastic Gradient Descent (SGD) by requiring twice the gradient calculations per optimization step. To mitigate this, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Jiaxin Deng , Junbiao Pang

Accelerated training algorithms, such as adaptive learning rates (or preconditioning) and various normalization methods, are widely used but not fully understood. When regularization is introduced, standard optimizers like adaptive learning…

Machine Learning · Computer Science 2025-12-30 Qiang Ye

With the success of deep neural networks (NNs) in a variety of domains, the computational and storage requirements for training and deploying large NNs have become a bottleneck for further improvements. Sparsification has consequently…

Machine Learning · Computer Science 2024-04-24 Nadav Joseph Outmezguine , Noam Levi