中文
相关论文

相关论文: Smoothing ADMM for Non-convex and Non-smooth Hiera…

200 篇论文

In this paper, we depart from the widely-used gradient descent-based hierarchical federated learning (FL) algorithms to develop a novel hierarchical FL framework based on the alternating direction method of multipliers (ADMM). Within this…

机器学习 · 计算机科学 2024-09-30 Seyed Mohammad Azimi-Abarghouyi , Nicola Bastianello , Karl H. Johansson , Viktoria Fodor

In this paper, we analyze the convergence of the alternating direction method of multipliers (ADMM) for minimizing a nonconvex and possibly nonsmooth objective function, $\phi(x_0,\ldots,x_p,y)$, subject to coupled linear equality…

最优化与控制 · 数学 2018-05-31 Yu Wang , Wotao Yin , Jinshan Zeng

Decentralized federated learning (FL) is a promising approach for training machine learning models on sensor networks, Internet of Things (IoT) devices, and other edge systems where no central server exists. While federated learning offers…

机器学习 · 计算机科学 2026-05-12 Akihito Taya , Yuuki Nishiyama , Kaoru Sezaki

Personalized federated learning (PFL) is an approach proposed to address the issue of poor convergence on heterogeneous data. However, most existing PFL frameworks require strong assumptions for convergence. In this paper, we propose an…

机器学习 · 计算机科学 2024-08-23 Shengkun Zhu , Jinshan Zeng , Sheng Wang , Yuan Sun , Zhiyong Peng

In this paper, we propose a unified framework of inexact stochastic Alternating Direction Method of Multipliers (ADMM) for solving nonconvex problems subject to linear constraints, whose objective comprises an average of finite-sum smooth…

最优化与控制 · 数学 2024-03-05 Yuxuan Zeng , Jianchao Bai , Shengjia Wang , Zhiguo Wang

This paper addresses the challenge of localization in federated settings, which are characterized by distributed data, non-convexity, and non-smoothness. To tackle the scalability and outlier issues inherent in such environments, we propose…

机器学习 · 计算机科学 2025-03-13 Reza Mirzaeifard , Ashkan Moradi , Masahiro Yukawa , Stefan Werner

Statistical heterogeneity is a root cause of tension among accuracy, fairness, and robustness of federated learning (FL), and is key in paving a path forward. Personalized FL (PFL) is an approach that aims to reduce the impact of…

机器学习 · 计算机科学 2024-07-24 Shengkun Zhu , Jinshan Zeng , Sheng Wang , Yuan Sun , Xiaodong Li , Yuan Yao , Zhiyong Peng

Federated learning (FL) is an emerging machine learning paradigm that allows to accomplish model training without aggregating data at a central server. Most studies on FL consider a centralized framework, in which a single server is endowed…

机器学习 · 计算机科学 2023-03-22 Bin Wang , Jun Fang , Hongbin Li , Xiaojun Yuan , Qing Ling

This study investigates clustered federated learning (FL), one of the formulations of FL with non-i.i.d. data, where the devices are partitioned into clusters and each cluster optimally fits its data with a localized model. We propose a…

机器学习 · 计算机科学 2023-12-27 Xue Yu , Ziyi Liu , Wu Wang , Yifan Sun

Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, traditional FL suffers from communication overhead, system heterogeneity, and straggler effects. Asynchronous…

机器学习 · 计算机科学 2025-08-05 Ali Forootani , Raffaele Iervolino

Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and systems, limited…

机器学习 · 计算机科学 2024-08-01 Yongcun Song , Ziqi Wang , Enrique Zuazua

Federated learning (FL), which has gained increasing attention recently, enables distributed devices to train a common machine learning (ML) model for intelligent inference cooperatively without data sharing. However, problems in practical…

机器学习 · 计算机科学 2022-11-01 Yujie Zhou , Zhidu Li , Tong Tang , Ruyan Wang

We propose a novel algorithm for solving the composite Federated Learning (FL) problem. This algorithm manages non-smooth regularization by strategically decoupling the proximal operator and communication, and addresses client drift without…

机器学习 · 计算机科学 2023-09-06 Jiaojiao Zhang , Jiang Hu , Mikael Johansson

Motivated by the emergence of federated learning (FL), we design and analyze federated methods for addressing: (i) Nondifferentiable nonconvex optimization; (ii) Bilevel optimization; (iii) Minimax problems; and (iv) Two-stage stochastic…

最优化与控制 · 数学 2025-07-04 Yuyang Qiu , Uday V. Shanbhag , Farzad Yousefian

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…

机器学习 · 计算机科学 2022-04-11 Yonghai Gong , Yichuan Li , Nikolaos M. Freris

Federated learning (FL) aims to train machine learning (ML) models collaboratively using decentralized data, bypassing the need for centralized data aggregation. Standard FL models often assume that all data come from the same unknown…

机器学习 · 计算机科学 2025-03-25 Wen Bai , Yi Wong , Xiao Qiao , Chin Pang Ho

Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a unified global model without the need to share data amongst each other. A major challenge in…

Federated Learning (FL) is an increasingly popular machine learning paradigm in which multiple nodes try to collaboratively learn under privacy, communication and multiple heterogeneity constraints. A persistent problem in federated…

机器学习 · 计算机科学 2022-02-24 Elnur Gasanov , Ahmed Khaled , Samuel Horváth , Peter Richtárik

The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generalize centralized…

机器学习 · 计算机科学 2022-07-18 Jiayin Jin , Jiaxiang Ren , Yang Zhou , Lingjuan Lyu , Ji Liu , Dejing Dou

Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private. With an increasing scale of clients and models, FL encounters two key challenges, client drift due…

机器学习 · 计算机科学 2025-01-20 Jianhui Sun , Xidong Wu , Heng Huang , Aidong Zhang
‹ 上一页 1 2 3 10 下一页 ›