Efficient and Reliable Overlay Networks for Decentralized Federated Learning

DOI10.1137/21M1465081OpenAlexW4297923983MaRDI QIDQ5102155

Yifan Hua, Chen Qian, Bao Wang, Kevin C. Miller, Andrea L. Bertozzi

Publication date: 6 September 2022

Published in: SIAM Journal on Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.15486

zbMATH Keywords

random graphsoverlay networksdecentralized federated learning

Mathematics Subject Classification ID

General topics in artificial intelligence (68T01) Distributed algorithms (68W15) Acceleration of convergence in numerical analysis (65B99) Computational aspects of data analysis and big data (68T09)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Eigenvalues and expanders
• Laplacians and the Cheeger inequality for directed graphs
• Explicit expanders of every degree and size
• On the Convergence of Decentralized Gradient Descent
• Expander graphs in pure and applied mathematics
• Expander codes
• Expander graphs and their applications
• An Elementary Construction of Constant-Degree Expanders
• Fastest Mixing Markov Chain on a Graph
• Distributed Subgradient Methods for Multi-Agent Optimization
• Some methods of speeding up the convergence of iteration methods