On early stopping of stochastic mirror descent method for ill-posed inverse problems
Open Access
- 6 March 2025
- journal article
- research article
- Published by Springer Nature in Numerische Mathematik
- Vol. 157 (2) , 539-571
Abstract
In recent years, stochastic algorithms have been introduced to solve ill-posed inverse problems. These algorithms select a random subset of equations during each iteration, displaying excellent scalability and competitive performance in large-scale inverse problems. However, given the inherent ill-posed nature of the underlying problems and the presence of noise in measurement data, these algorithms often exhibit prominent oscillations and display a semi-convergence phenomenon, like all iterative regularization methods. This aspect poses challenges in obtaining an output with good approximation property. In this paper, by leveraging the spirit of the discrepancy principle we propose an a posteriori stopping rule for the stochastic mirror descent method for solving ill-posed inverse problems in Banach spaces. We show that the proposed stopping rule always terminates the method within a finite number of steps and the corresponding outcome converges toward the sought solution almost surely as the noise level approaches zero. Numerical simulations are reported to demonstrate the promising performance.Keywords
Funding Information
- Australian National University
This publication has 22 references indexed in Scilit:
- Convergence rates of a dual gradient method for constrained linear ill-posed problemsNumerische Mathematik, 2022
- Stochastic gradient descent for linear inverse problems in Hilbert spacesMathematics of Computation, 2021
- A revisit on Landweber iterationInverse Problems, 2020
- The numerics of phase retrievalActa Numerica, 2020
- A Basic Course in Probability Theory2016
- Regularization of Inverse Problems1996
- A convergence analysis of the Landweber iteration for nonlinear ill-posed problemsNumerische Mathematik, 1995
- Maximum Entropy Regularization for Fredholm Integral Equations of the First KindSIAM Journal on Mathematical Analysis, 1993
- Convergence Rates for Maximum Entropy RegularizationSIAM Journal on Numerical Analysis, 1993
- Linear inverse problems with discrete data. I. General formulation and singular system analysisInverse Problems, 1985