咨询与建议

限定检索结果

文献类型

  • 2 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 3 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 1 篇 电气工程
    • 1 篇 计算机科学与技术...
  • 1 篇 理学
    • 1 篇 物理学

主题

  • 3 篇 constrained non-...
  • 1 篇 bayesian posteri...
  • 1 篇 personalized fed...
  • 1 篇 multiplex networ...
  • 1 篇 averaged true ri...
  • 1 篇 convergence
  • 1 篇 vectors
  • 1 篇 servers
  • 1 篇 link overlap
  • 1 篇 byzantine-robust...
  • 1 篇 computational mo...
  • 1 篇 inter-layer comm...
  • 1 篇 kl divergence
  • 1 篇 bounded non-nega...
  • 1 篇 signal processin...
  • 1 篇 fixed point equa...
  • 1 篇 convex optimizat...
  • 1 篇 federated learni...
  • 1 篇 generalized pins...
  • 1 篇 high probability...

机构

  • 1 篇 sun yat sen univ...
  • 1 篇 kth royal inst t...
  • 1 篇 indian inst tech...
  • 1 篇 univ tehran coll...

作者

  • 1 篇 huang yue
  • 1 篇 ling qing
  • 1 篇 zhang jiaojiao
  • 1 篇 hemachandra nand...
  • 1 篇 he xuechao
  • 1 篇 abdolhosseini-qo...
  • 1 篇 sahu puja
  • 1 篇 yazdani naser
  • 1 篇 asadpour masoud

语言

  • 2 篇 英文
  • 1 篇 其他
检索条件"主题词=constrained non-convex optimization"
3 条 记 录,以下是1-10 订阅
排序:
Byzantine-Robust and Communication-Efficient Personalized Federated Learning
收藏 引用
IEEE TRANSACTIONS ON SIGNAL PROCESSING 2025年 73卷 26-39页
作者: Zhang, Jiaojiao He, Xuechao Huang, Yue Ling, Qing Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China KTH Royal Inst Technol Div Decis & Control Syst S-11428 Stockholm Sweden
This paper explores constrained non-convex personalized federated learning (PFL), in which a group of workers train local models and a global model, under the coordination of a server. To address the challenges of eff... 详细信息
来源: 评论
Overlapping communities and the prediction of missing links in multiplex networks
收藏 引用
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2020年 554卷 124650-124650页
作者: Abdolhosseini-Qomi, Amir Mahdi Yazdani, Naser Asadpour, Masoud Univ Tehran Coll Engn Dept Elect & Comp Engn Tehran Iran
Multiplex networks are a representation of real-world complex systems as a set of entities (i.e. nodes) connected via different types of connections (i.e. layers). The observed connections in these networks may not be... 详细信息
来源: 评论
Optimal PAC-Bayesian Posteriors for Stochastic Classifiers and their use for Choice of SVM Regularization Parameter  11
Optimal PAC-Bayesian Posteriors for Stochastic Classifiers a...
收藏 引用
11th Asian Conference on Machine Learning (ACML)
作者: Sahu, Puja Hemachandra, Nandyala Indian Inst Technol Mumbai Maharashtra India
PAC-Bayesian set up involves a stochastic classifier characterized by a posterior distribution on a classifier set, offers a high probability bound on its averaged true risk and is robust to the training sample used. ... 详细信息
来源: 评论