Decentralized learning for wireless communications and networking

DOI10.1007/978-3-319-41589-5_14zbMATH Open1420.68168arXiv1503.08855OpenAlexW1943968880MaRDI QIDQ5350486FDOQ5350486

Authors: Qing Ling, Gonzalo Mateos, Ioannis D. Schizas, Hao Zhu, Georgios B. Giannakis 

Publication date: 1 September 2017

Published in: Splitting Methods in Communication, Imaging, Science, and Engineering (Search for Journal in Brave)

Abstract: This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data. A generic learning problem is formulated and recast into a separable form, which is iteratively minimized using the alternating-direction method of multipliers (ADMM) so as to gain the desired degree of parallelization. Without exchanging elements from the distributed training sets and keeping inter-node communications at affordable levels, the local (per-node) learners consent to the desired quantity inferred globally, meaning the one obtained if the entire training data set were centrally available. Impact of the decentralized learning framework to contemporary wireless communications and networking tasks is illustrated through case studies including target tracking using wireless sensor networks, unveiling Internet traffic anomalies, power system state estimation, as well as spectrum cartography for wireless cognitive radio networks.

Full work available at URL: https://arxiv.org/abs/1503.08855

Recommendations

• Online learning over a decentralized network through ADMM
• Decentralized dictionary learning over time-varying digraphs
• Adaptation, learning, and optimization over networks
• GADMM: fast and communication efficient framework for distributed machine learning
• Decentralized optimization over tree graphs

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Distributed algorithms (68W15)

Cited In (7)

• Over-the-Air computation for distributed machine learning and consensus in large wireless networks
• Perturbed proximal primal-dual algorithm for nonconvex nonsmooth optimization
• An approximation proximal gradient algorithm for nonconvex-linear minimax problems with nonconvex nonsmooth terms
• Sparsity promoting decentralized learning strategies for radio tomographic imaging using consensus based ADMM approach
• Alternating direction method of multipliers for a class of nonconvex bilinear optimization: convergence analysis and applications
• A divide-and-conquer algorithm for distributed optimization on networks
• A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems

This page was built for publication: Decentralized learning for wireless communications and networking

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5350486)