Výsledky vyhledávání - "Li, Yangchen"

Report

GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing Systems

Autor: Li, Yangchen, Cui, Ying, Lau, Vincent

The optimal implementation of federated learning (FL) in practical edge computing systems has been an outstanding problem. In this paper, we propose an optimization-based quantized FL algorithm, which can appropriately fit a general edge computing sy

Externí odkaz: http://arxiv.org/abs/2306.07497

Zobrazit plný text záznamu

Akademický článek

Akkermansia Muciniphila supplementation improves hyperlipidemia, cardiac function, and gut microbiota in high fat fed apolipoprotein E–deficient mice

Autor: Xiao, Xiao, Wu, Yuanyuan, Jie, Zhuye, Lin, Lu, Li, Yangchen, Hu, Weixian, Li, Yong, Zhong, Shilong

Publikováno v: In Prostaglandins and Other Lipid Mediators December 2024 175

Zobrazit plný text záznamu

Report

An Optimization Framework for Federated Edge Learning

Autor: Li, Yangchen, Cui, Ying, Lau, Vincent

The optimal design of federated learning (FL) algorithms for solving general machine learning (ML) problems in practical edge computing systems with quantized message passing remains an open problem. This paper considers an edge computing system wher

Externí odkaz: http://arxiv.org/abs/2111.13526

Zobrazit plný text záznamu

Report

Optimization-Based GenQSGD for Federated Edge Learning

Autor: Li, Yangchen, Cui, Ying, Lau, Vincent

Optimal algorithm design for federated learning (FL) remains an open problem. This paper explores the full potential of FL in practical edge computing systems where workers may have different computation and communication capabilities, and quantized

Externí odkaz: http://arxiv.org/abs/2110.12987

Zobrazit plný text záznamu

Report

Sample-based and Feature-based Federated Learning for Unconstrained and Constrained Nonconvex Optimization via Mini-batch SSCA

Autor: Cui, Ying, Li, Yangchen, Ye, Chencheng

Federated learning (FL) has become a hot research area in enabling the collaborative training of machine learning models among multiple clients that hold sensitive local data. Nevertheless, unconstrained federated optimization has been studied mainly

Externí odkaz: http://arxiv.org/abs/2104.06011

Zobrazit plný text záznamu