Decentralized Online Regularized Learning Over Random Time-Varying Graphs

arXiv:2206.03861v4 Announce Type: replace
Abstract: We study the decentralized online regularized linear regression algorithm over random time-varying graphs. At each time step, every node runs an online estimation algorithm consisting of an innovation term processing its own new measurement, a consensus term taking a weighted sum of estimations of its own and its neighbors with additive and multiplicative communication noises and a regularization term preventing over-fitting. It is not required that the regression matrices and graphs satisfy special statistical assumptions …

abstract algorithm arxiv consensus cs.lg cs.sy decentralized eess.sy estimations every graphs innovation linear linear regression measurement node processing random regression stat.ml study sum type