Search

In this work, we present a novel variant of the stochastic gradient descent method termed as iteratively regularized stochastic gradient descent (IRSGD) method to solve nonlinear ill-posed problems in Hilbert spaces. Under standard assumptions, we demonstrate that the mean square iteration error of the method converges to zero for exact data. In the presence of noisy data, we first propose a heuristic parameter choice rule (HPCR) based on the method suggested by Hanke and Raus, and then apply the IRSGD method in combination with HPCR. Precisely, HPCR selects the regularization parameter without requiring any a-priori knowledge of the noise level. We show that the method terminates in finitely many steps in case of noisy data and has regularizing features. Further, we discuss the convergence rates of the method using well-known source and other related conditions under HPCR as well as discrepancy principle. To the best of our knowledge, this is the first work that establishes both the regularization properties and convergence rates of a stochastic gradient method using a heuristic type rule in the setting of infinite-dimensional Hilbert spaces. Finally, we provide the numerical experiments to showcase the practical efficacy of the proposed method.

In this study, we present and analyze a novel variant of the stochastic gradient descent method, referred as Stochastic data-driven Bouligand Landweber iteration tailored for addressing the system of non-smooth ill-posed inverse problems. Our method incorporates the utilization of training data, using a bounded linear operator, which guides the iterative procedure. At each iteration step, the method randomly chooses one equation from the nonlinear system with data-driven term. When dealing with the precise or exact data, it has been established that mean square iteration error converges to zero. However, when confronted with the noisy data, we employ our approach in conjunction with a predefined stopping criterion, which we refer to as an \textit{a-priori} stopping rule. We provide a comprehensive theoretical foundation, establishing convergence and stability for this scheme within the realm of infinite-dimensional Hilbert spaces. These theoretical underpinnings are further bolstered by discussing an example that fulfills assumptions of the paper.