English
Related papers

Related papers: FedAdamW: A Communication-Efficient Optimizer with…

200 papers

Balancing convergence efficiency and robustness under Differential Privacy (DP) is a central challenge in Federated Learning (FL). While AdamW accelerates training and fine-tuning in large-scale models, we find that directly applying it to…

Machine Learning · Computer Science 2026-04-21 Jin Liu , Yinbin Miao , Ning Xi , Junkang Liu

Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that…

Machine Learning · Computer Science 2026-05-07 JiangBo Zhao , ZhaoXin Liu

Adaptive optimizers with decoupled weight decay, such as AdamW, are the de facto standard for pre-training large transformer-based generative models. Yet the quadratic nature of the $\ell_2$ penalty embedded in weight decay drives all…

Machine Learning · Computer Science 2025-11-19 Fu-Ming Guo , Yingfang Fan

Adaptive optimization has achieved notable success for distributed learning while extending adaptive optimizer to federated Learning (FL) suffers from severe inefficiency, including (i) rugged convergence due to inaccurate gradient…

Machine Learning · Computer Science 2023-08-02 Yan Sun , Li Shen , Hao Sun , Liang Ding , Dacheng Tao

Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with $\ell_2$ regularization in terms of generalization and optimization. However, this…

Machine Learning · Computer Science 2024-04-09 Shuo Xie , Zhiyuan Li

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

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

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization…

Machine Learning · Computer Science 2026-05-21 Meng Zhu , Quan Xiao , Weidong Min

In this paper, we introduce weight prediction into the AdamW optimizer to boost its convergence when training the deep neural network (DNN) models. In particular, ahead of each mini-batch training, we predict the future weights according to…

Machine Learning · Computer Science 2023-08-09 Lei Guan

The core bottleneck of Federated Learning (FL) lies in the communication rounds. That is, how to achieve more effective local updates is crucial for reducing communication rounds. Existing FL methods still primarily use element-wise local…

Machine Learning · Computer Science 2025-11-03 Junkang Liu , Fanhua Shang , Junchao Zhou , Hongying Liu , Yuanyuan Liu , Jin Liu

Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving privacy and enhancing security. However, data heterogeneity…

Machine Learning · Computer Science 2025-03-21 Changlong Shi , He Zhao , Bingjie Zhang , Mingyuan Zhou , Dandan Guo , Yi Chang

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms…

Machine Learning · Computer Science 2026-02-06 Hao Chen , Jinghui Yuan , Hanmin Zhang

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold…

Machine Learning · Computer Science 2025-09-22 Xiumei Deng , Jun Li , Kang Wei , Long Shi , Zehui Xiong , Ming Ding , Wen Chen , Shi Jin , H. Vincent Poor

Federated learning has allowed the training of statistical models over remote devices without the transfer of raw client data. In practice, training in heterogeneous and large networks introduce novel challenges in various aspects like…

Machine Learning · Computer Science 2020-11-17 Dipankar Sarkar , Sumit Rai , Ankur Narang

To address the communication burden issues associated with federated learning (FL), decentralized federated learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates…

Machine Learning · Computer Science 2023-08-17 Qinglun Li , Li Shen , Guanghao Li , Quanjun Yin , Dacheng Tao

Federated Learning (FL) is an emerging framework for distributed processing of large data volumes by edge devices subject to limited communication bandwidths, heterogeneity in data distributions and computational resources, as well as…

Machine Learning · Computer Science 2022-04-11 Yonghai Gong , Yichuan Li , Nikolaos M. Freris

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

Federated learning is a machine learning training paradigm that enables clients to jointly train models without sharing their own localized data. However, the implementation of federated learning in practice still faces numerous challenges,…

Machine Learning · Computer Science 2023-04-21 Yujia Wang , Lu Lin , Jinghui Chen

Federated learning is an emerging distributed machine learning framework which jointly trains a global model via a large number of local devices with data privacy protections. Its performance suffers from the non-vanishing biases introduced…

Machine Learning · Computer Science 2023-07-06 Yan Sun , Li Shen , Tiansheng Huang , Liang Ding , Dacheng Tao

The internal structure and operation mechanism of large-scale language models are analyzed theoretically, especially how Transformer and its derivative architectures can restrict computing efficiency while capturing long-term dependencies.…

Machine Learning · Computer Science 2024-05-21 Taiyuan Mei , Yun Zi , Xiaohan Cheng , Zijun Gao , Qi Wang , Haowei Yang
‹ Prev 1 2 3 10 Next ›