Decentralized diffusion-based learning under non-parametric limited prior knowledge

2023/05/05 by Paweł Wachel, Wachel, Paweł, Krzysztof Kowalczyk +3
Computer Science · #Blind Source Separation Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multiagent Systems (cs.MA) #Neural Networks Stability and Synchronization #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2305.03295

openalex publication_date 2023/05/05 · openalex created_date 2023/05/18 · openalex updated_date 2026/07/28

Abstract

We study the problem of diffusion-based network learning of a nonlinear phenomenon, m, from local agents' measurements collected in a noisy environment. For a decentralized network and information spreading merely between directly neighboring nodes, we propose a non-parametric learning algorithm, that avoids raw data exchange and requires only mild a priori knowledge about m. Non-asymptotic estimation error bounds are derived for the proposed method. Its potential applications are illustrated through simulation experiments.

Related

• Kernel-based learning with guarantees for multi-agent applications
• Diffusion Adaptation Strategies for Distributed Optimization and Learning over Networks
• Distributed Learning in Non-Convex Environments—Part I: Agreement at a Linear Rate
• Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate
• Diffusion Adaptation over Networks