Distributed Random Reshuffling Over Networks
Author:
Affiliation:
1. School of Data Science, Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China
2. School of Data Science, The Chinese University of Hong Kong, Shenzhen, China
Funder
Internal Program of Shenzhen Research Institute of Big Data
National Natural Science Foundation of China
Shenzhen Science and Technology Program
Fundamental Research Fund – Shenzhen Research Institute of Big Data
Shenzhen Research Institute of Big Data
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Electrical and Electronic Engineering,Signal Processing
Link
http://xplorestaging.ieee.org/ielx7/78/10040758/10081450.pdf?arnumber=10081450
Reference54 articles.
1. Asymptotic Network Independence in Distributed Stochastic Optimization for Machine Learning: Examining Distributed and Centralized Stochastic Gradient Descent
2. Improving the Transient Times for Distributed Stochastic Gradient Methods
3. A fast randomized incremental gradient method for decentralized non-convex optimization
4. Variance-Reduced Decentralized Stochastic Optimization With Accelerated Convergence
5. Gradient-based learning applied to document recognition
Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Shuffling-type gradient method with bandwidth-based step sizes for finite-sum optimization;Neural Networks;2024-11
2. Distributed Stochastic Optimization Under a General Variance Condition;IEEE Transactions on Automatic Control;2024-09
3. UAdam: Unified Adam-Type Algorithmic Framework for Nonconvex Optimization;Neural Computation;2024-08-19
4. On Improved Distributed Random Reshuffling over Networks;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
5. mPage: Probabilistic Gradient Estimator With Momentum for Non-Convex Optimization;IEEE Transactions on Signal Processing;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3