DECENTRALIZED DIFFUSION-BASED LEARNING UNDER NON-PARAMETRIC LIMITED PRIOR KNOWLEDGE

作     者：Wachel, Pawel Kowalczyk, Krzysztof Rojas, Cristian R. 

作者机构：Department of Control Systems and Mechatronics Wroclaw University of Science and Technology Wroclaw Poland School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Electronic data interchange 

摘      要：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. Copyright © 2023, The Authors. All rights reserved.