English
Related papers

Related papers: Correction of Decoupled Weight Decay

200 papers

Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness assumptions on the loss function to explain the advantages of…

Machine Learning · Computer Science 2025-12-02 Robin Yadav , Shuo Xie , Tianhao Wang , Zhiyuan Li

Optimizers leveraging the matrix structure in neural networks, such as Shampoo and Muon, are more data-efficient than element-wise algorithms like Adam and Signum. While in specific settings, Shampoo and Muon reduce to spectral descent…

Machine Learning · Computer Science 2026-02-11 Runa Eschenhagen , Anna Cai , Tsung-Hsien Lee , Hao-Jun Michael Shi

Recent work [4] analyses the local convergence of Adam in a neighbourhood of an optimal solution for a twice-differentiable function. It is found that the learning rate has to be sufficiently small to ensure local stability of the optimal…

Machine Learning · Computer Science 2021-12-14 Guoqiang Zhang , Niwa Kenta , W. Bastiaan Kleijn

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" through a series of…

Machine Learning · Computer Science 2025-06-17 Teodora Srećković , Jonas Geiping , Antonio Orvieto

Decentralized optimization is effective to save communication in large-scale machine learning. Although numerous algorithms have been proposed with theoretical guarantees and empirical successes, the performance limits in decentralized…

Machine Learning · Computer Science 2022-10-17 Kun Yuan , Xinmeng Huang , Yiming Chen , Xiaohan Zhang , Yingya Zhang , Pan Pan

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

Data-enabled predictive control (DeePC) is a recently established form of Model Predictive Control (MPC), based on behavioral systems theory. While eliminating the need to explicitly identify a model, it requires an additional…

Systems and Control · Electrical Eng. & Systems 2023-05-02 Manuel Koch , Colin N. Jones

In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the…

Machine Learning · Computer Science 2025-10-17 Zixi Wang , Yushe Cao , Yubo Huang , Jinzhu Wei , Jingzehua Xu , Shuai Zhang , Xin Lai

Presently the most successful approaches to semi-supervised learning are based on consistency regularization, whereby a model is trained to be robust to small perturbations of its inputs and parameters. To understand consistency…

Machine Learning · Computer Science 2019-02-22 Ben Athiwaratkun , Marc Finzi , Pavel Izmailov , Andrew Gordon Wilson

Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization, even with homogeneous data distributions. This work…

Machine Learning · Computer Science 2026-02-04 Zesen Wang , Mikael Johansson

Adam is widely recognized as one of the most effective optimizers for training deep neural networks (DNNs). Despite its remarkable empirical success, its theoretical convergence analysis remains unsatisfactory. Existing works predominantly…

Machine Learning · Computer Science 2025-07-10 Hanyang Peng , Shuang Qin , Yue Yu , Fangqing Jiang , Hui Wang , Zhouchen Lin

We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. This approach capitalizes on the inherent superposition property of wireless channels,…

Machine Learning · Computer Science 2024-03-12 Chenhao Wang , Zihan Chen , Nikolaos Pappas , Howard H. Yang , Tony Q. S. Quek , H. Vincent Poor

Stochastic Gradient Descent (SGD) is a central tool in machine learning. We prove that SGD converges to zero loss, even with a fixed (non-vanishing) learning rate - in the special case of homogeneous linear classifiers with smooth monotone…

Machine Learning · Statistics 2022-04-19 Mor Shpigel Nacson , Nathan Srebro , Daniel Soudry

Adaptive optimization algorithms, particularly Adam and its variant AdamW, are fundamental components of modern deep learning. However, their training dynamics lack comprehensive theoretical understanding, with limited insight into why…

Machine Learning · Computer Science 2024-12-23 Rhys Gould , Hidenori Tanaka

The concept of learning to optimize involves utilizing a trainable optimization strategy rather than relying on manually defined full gradient estimations such as ADAM. We present a framework that jointly trains the full gradient estimator…

Machine Learning · Computer Science 2026-01-30 Ruiqi Wang , Diego Klabjan

We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…

Machine Learning · Computer Science 2026-02-03 Aikaterini Karoni , Rajit Rajpal , Benedict Leimkuhler , Gabriel Stoltz

In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance. This issue is usually tackled by delay tolerant algorithms with some mild assumptions on the objective…

Machine Learning · Computer Science 2024-10-28 Haoxiang Wang , Zhanhong Jiang , Chao Liu , Soumik Sarkar , Dongxiang Jiang , Young M. Lee

Although ADAM is a very popular algorithm for optimizing the weights of neural networks, it has been recently shown that it can diverge even in simple convex optimization examples. Several variants of ADAM have been proposed to circumvent…

Optimization and Control · Mathematics 2020-09-25 Anas Barakat , Pascal Bianchi

Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly…

Machine Learning · Computer Science 2021-07-20 Zhou Shao , Tong Lin

We investigate the convergence rates and data sample sizes required for training a machine learning model using a stochastic gradient descent (SGD) algorithm, where data points are sampled based on either their loss value or uncertainty…

Machine Learning · Computer Science 2024-11-26 Daniel Haimovich , Dima Karamshuk , Fridolin Linder , Niek Tax , Milan Vojnovic
‹ Prev 1 3 4 5 6 7 10 Next ›