Over-the-Air computation for distributed machine learning and consensus in large wireless networks

DOI10.1007/978-3-031-09745-4_13zbMath1504.94037OpenAlexW4312639269MaRDI QIDQ2106494

Igor Bjelaković, Matthias Frey, Slawomir Stanczak

Publication date: 14 December 2022

Full work available at URL: https://doi.org/10.1007/978-3-031-09745-4_13

zbMATH Keywords

distributed consensusanalog Over-the-Air computationfast-fading wireless channelsvertical federated learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (1)

Over-the-Air computation for distributed machine learning and consensus in large wireless networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency of support vector machines using additive kernels for additive models
• Simultaneous channels
• Almost independence of random variables and capacity of a secrecy channel
• Over-the-Air computation for distributed machine learning and consensus in large wireless networks
• Semantic Security for the Wiretap Channel
• Expanding the Compute-and-Forward Framework: Unequal Powers, Signal Levels, and Multiple Linear Combinations
• Network Information Theory
• Consensus of Subjective Probabilities: The Pari-Mutuel Method
• The Capacity of a Class of Channels
• Support Vector Machines
• Computation Over Multiple-Access Channels
• Nomographic Functions are Nowhere Dense
• Consensus theoretic classification methods
• The common information of two dependent random variables
• How to encode the modulo-two sum of binary sources (Corresp.)
• Approximation theory of output statistics
• Analysis of Max-Consensus Algorithms in Wireless Channels
• Harnessing Interference for Analog Function Computation in Wireless Sensor Networks
• Consensus and Cooperation in Networked Multi-Agent Systems
• Distributed Compressive Sensing: A Deep Learning Approach
• Non-Gaussian noise models in signal processing for telecommunications: new methods an results for class A and class B noise models
• Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• On Analog Gradient Descent Learning Over Multiple Access Fading Channels
• Computation Scheduling for Distributed Machine Learning With Straggling Workers
• Compute-and-Forward: Harnessing Interference Through Structured Codes
• Flocking for Multi-Agent Dynamic Systems: Algorithms and Theory
• Coding theorems for the compound semi-continuous memoryless channels
• Strong Secrecy From Channel Resolvability
• Capacity of Classes of Gaussian Channels
• Some remarks on the capacity of compound channels in the semicontinuous case

This page was built for publication: Over-the-Air computation for distributed machine learning and consensus in large wireless networks