Online Distributed Learning Over Networks in RKH Spaces Using Random Fourier Features

DOI10.1109/TSP.2017.2781640zbMATH Open1414.94015arXiv1703.08131OpenAlexW2599228073MaRDI QIDQ4621707FDOQ4621707

Authors: P. Bouboulis, Symeon Chouvardas, Sergios Theodoridis 

Publication date: 12 February 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: We present a novel diffusion scheme for online kernel-based learning over networks. So far, a major drawback of any online learning algorithm, operating in a reproducing kernel Hilbert space (RKHS), is the need for updating a growing number of parameters as time iterations evolve. Besides complexity, this leads to an increased need of communication resources, in a distributed setting. In contrast, the proposed method approximates the solution as a fixed-size vector (of larger dimension than the input space) using Random Fourier Features. This paves the way to use standard linear combine-then-adapt techniques. To the best of our knowledge, this is the first time that a complete protocol for distributed online learning in RKHS is presented. Conditions for asymptotic convergence and boundness of the networkwise regret are also provided. The simulated tests illustrate the performance of the proposed scheme.

Full work available at URL: https://arxiv.org/abs/1703.08131

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Application of orthogonal and other special functions (94A11)

Cited In (3)

• Title not available (Why is that?)
• Decentralized learning over a network with Nyström approximation using SGD
• Random feature-based online multi-kernel learning in environments with unknown dynamics

This page was built for publication: Online Distributed Learning Over Networks in RKH Spaces Using Random Fourier Features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621707)