Decentralized diffusion-based learning under non-parametric limited prior knowledge
This addresses decentralized learning in networks with limited prior knowledge, but appears incremental as it builds on existing diffusion-based methods.
The paper tackles decentralized learning of a nonlinear phenomenon from noisy local measurements in a network, proposing a non-parametric algorithm that avoids raw data exchange and requires minimal prior knowledge, with non-asymptotic error bounds derived and simulations illustrating potential applications.
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 \textit{a priori} knowledge about $m$. Non-asymptotic estimation error bounds are derived for the proposed method. Its potential applications are illustrated through simulation experiments.