BANDIT

作品数:38被引量:15H指数:3
导出分析报告
相关领域:自动化与计算机技术交通运输工程更多>>
相关作者:万贻平张东戈高海宾袁德明王聪更多>>
相关机构:重庆师范大学南京信息工程大学华南理工大学南京理工大学更多>>
相关期刊:《The Journal of China Universities of Posts and Telecommunications》《摩托车趋势》《Digital Communications and Networks》《计算机与现代化》更多>>
相关基金:国家自然科学基金重庆市自然科学基金上海市浦江人才计划项目中国博士后科学基金更多>>
-

检索结果分析

结果分析中...
条 记 录,以下是1-10
视图:
排序:
具有反馈延迟分布式在线复合优化的动态遗憾性能
《自动化学报》2025年第4期835-856,共22页侯瑞捷 李修贤 易新蕾 洪奕光 谢立华 
国家自然科学基金(62473292,62088101);上海市科技重大专项(2021SHZDZX0100)资助。
研究分布式在线复合优化场景中的几种反馈延迟,包括梯度反馈、单点Bandit反馈和两点Bandit反馈.其中,每个智能体的局部目标函数由一个强凸光滑函数与一个凸的非光滑正则项组成.在分布式场景下,研究每个智能体具有不同时变延迟的场景.基...
关键词:分布式在线凸优化 复合优化 反馈延迟 BANDIT 反馈 动态遗憾 
分布式在线鞍点问题的Bandit反馈优化算法
《自动化学报》2025年第4期857-874,共18页张文韬 张保勇 袁德明 徐胜元 
国家自然科学基金(62273181,62373190,62221004)资助。
本文研究了多智能体时变网络上基于Bandit反馈的分布式在线鞍点问题,其中每个智能体通过本地计算和局部信息交流去协作最小化全局损失函数.在Bandit反馈下,包括梯度在内的损失函数信息是不可用的,每个智能体仅能获得和使用在某决策或其...
关键词:BANDIT 反馈 分布式优化 在线鞍点问题 镜面下降 动态鞍点遗憾 
Existence and uniqueness of mean field equilibrium in continuous bandit game
《Science China(Information Sciences)》2025年第3期391-392,共2页Xiong WANG Yuqing LI Riheng JIA 
supported by National Key Research and Development Program of China(Grant No.2022ZD0115301);Fundamental Research Funds for the Central Universities(Grant No.2042023kf0120);National Natural Science Foundation of China(Grant Nos.62272417,62202185,62302343);Guangdong Basic and Applied Basic Research Foundation(Grant No.2022A1515110396)。
Multiarmed bandit(MAB)models are widely used for sequential decision-making in uncertain environments,such as resource allocation in computer communication systems.A critical challenge in interactive multiagent system...
关键词:EQUILIBRIUM UNIQUENESS EXISTENCE 
Privacy Preserving Distributed Bandit Residual Feedback Online Optimization Over Time-Varying Unbalanced Graphs
《IEEE/CAA Journal of Automatica Sinica》2024年第11期2284-2297,共14页Zhongyuan Zhao Zhiqiang Yang Luyao Jiang Ju Yang Quanbo Ge 
supported by the National Natural Science Foundation of China (62033010, U23B2061);Qing Lan Project of Jiangsu Province(R2023Q07)。
This paper considers the distributed online optimization(DOO) problem over time-varying unbalanced networks, where gradient information is explicitly unknown. To address this issue, a privacy-preserving distributed on...
关键词:Differential privacy distributed online optimization(DOO) federated learning one-point residual feedback(OPRF) time-varying unbalanced graphs 
Age-of-Information-Aware Federated Learning
《Journal of Computer Science & Technology》2024年第3期637-653,共17页徐殷 肖明军 吴晨 吴杰 周津锐 孙贺 
supported by the National Natural Science Foundation of China under Grant No.62172386;the Natural Science Foundation of Jiangsu Province of China under Grant No.BK20231212;the Teaching Research Project of the Education Department of Anhui Province of China under Grant No.2021jyxm1738.
Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private ...
关键词:federated learning Age of Information restless multi-armed bandit Whittle’s index 
基于Fed-DPDOBO的分散式联邦学习
《计算机与现代化》2024年第4期99-106,共8页杨巨 邓志良 杨志强 王燕 赵中原 
江苏省自然科学基金资助项目(BK20200824);江苏省研究生科研与实践创新计划项目(SJCX23_0391)。
传统的客户-服务器架构联邦学习作为解决数据孤岛问题的有效手段,其中心服务器面临着巨大的带宽压力,分散式的对等架构联邦学习在一定程度上可改善这种情况。然而,联邦学习的客户端还存在着数据隐私泄露的风险,而且其成本函数梯度信息...
关键词:数据孤岛 联邦学习 一致性约束 对等架构 差分隐私 单点Bandit 
Distributed online bandit tracking for Nash equilibrium under partial-decision information setting
《Science China(Technological Sciences)》2023年第11期3129-3138,共10页FENG ZhangCheng XU WenYing CAO JinDe YANG ShaoFu RUTKOWSKI Leszek 
supported by the National Natural Science Foundation of China(Grant Nos.62173087,62176056,and 61833005);the Fundamental Research Funds for the Central Universities;in part by the Alexander von Humboldt Foundation of Germany;supported by Zhi Shan Youth Scholar Program from Southeast University;by Young Elite Scientists Sponsorship Program by CAST(Grant No.2021QNRC001)。
This paper is concerned with a Nash equilibrium(NE)tracking issue in online games with bandit feedback,where cost functions vary with time and agents only have access to the values of these functions at two points dur...
关键词:online game bandit feedback partial-decision two-point gradient estimator 
Stochastic programming based multi-arm bandit offloading strategy for internet of things
《Digital Communications and Networks》2023年第5期1200-1211,共12页Bin Cao Tingyong Wu Xiang Bai 
This work was supported in part by the Zhejiang Lab under Grant 20210AB02;in part by the Sichuan International Science and Technology Innovation Cooperation/Hong Kong,Macao and Taiwan Science and Technology Innovation Cooperation Project under Grant 2019YFH0163;in part by the Key Research and Development Project of Sichuan Provincial Department of Science and Technology under Grant 2018JZ0071.
In order to solve the high latency of traditional cloud computing and the processing capacity limitation of Internet of Things(IoT)users,Multi-access Edge Computing(MEC)migrates computing and storage capabilities from...
关键词:Multi-access computing Internet of things OFFLOADING Stochastic programming Multi-arm bandit 
基于Bandit反馈的自适应量化分布式在线镜像下降算法
《控制理论与应用》2023年第10期1774-1782,共9页谢俊如 高文华 谢奕彬 
国家自然科学基金项目(62273157);广州市科技计划项目(202002030158)资助。
多智能体系统的在线分布式优化常用于处理动态环境下的优化问题,节点间需要实时传输数据流.在很多情况下,各节点无法获取个体目标函数的全部信息(包括梯度信息),并且节点间信息传输存在一定的通信约束.考虑到非欧投影意义下的镜像下降...
关键词:镜像下降算法 多智能体系统 优化 量化 Bandit反馈 
Channel estimation based on multi-armed approach for maritime OFDM wireless communications
《The Journal of China Universities of Posts and Telecommunications》2023年第4期75-85,120,共12页Zhang Qianqian Xu Yanli 
supported by the Natural Science Foundation Project of Shanghai(20ZR1423200);the Innovation Program of Shanghai Municipal Education Commission(2021-01-07-00-10-E00121)。
With the development of maritime informatization and the increased generation of marine data,the demands of efficient and reliable maritime communication surge.However,harsh and dynamic marine communication environmen...
关键词:MARITIME WIRELESS COMMUNICATIONS channel estimation multi-armed BANDIT 
检索报告 对象比较 聚类工具 使用帮助 返回顶部