Convergence Conditions of Online Regularized Statistical Learning in Reproducing Kernel Hilbert Space With Non-Stationary Data

arXiv:2404.03211v1 Announce Type: new
Abstract: We study the convergence of recursive regularized learning algorithms in the reproducing kernel Hilbert space (RKHS) with dependent and non-stationary online data streams. Firstly, we study the mean square asymptotic stability of a class of random difference equations in RKHS, whose non-homogeneous terms are martingale difference sequences dependent on the homogeneous ones. Secondly, we introduce the concept of random Tikhonov regularization path, and show that if the regularization path is slowly time-varying in some sense, …

abstract algorithms arxiv class convergence cs.lg cs.sy data data streams difference eess.sy kernel mean random recursive space square stability statistical study type