Stochastic linear regularization methods: random discrepancy principle and applications

DOI10.1088/1361-6420/AD149EMaRDI QIDQ6136777zbMATH OpenOpenAlexFDO

Authors Ye Zhang, Chuchu Chen

Publication date 17 January 2024

Published in Inverse Problems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1088/1361-6420/ad149e

zbMATH Keywords

convergenceill-posed problemsmartingalesrandom discrepancy principlestochastic linear regularization method

Mathematics Subject Classification ID

Numerical solutions to equations with linear operators (65J10) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)

Recommendations

• Stopping rules for Landweber-type iteration
• On the Convergence of Stochastic Gradient Descent for Nonlinear Ill-Posed Problems
• A stochastic iteratively regularized Gauss-Newton method
• Optimal adaptation for early stopping in statistical inverse problems

Cites work

• A CCBM-based generalized GKB iterative regularization algorithm for inverse Cauchy problems
• A new class of accelerated regularization methods, with application to bioluminescence tomography
• A Tikhonov regularization method for Cauchy problem based on a new relaxation model
• An adaptive regularization algorithm for recovering the rate constant distribution from biosensor data
• Estimating the rate constant from biosensor data via an adaptive variational Bayesian approach
• Finding frequent items in data streams
• scientific article; zbMATH DE number 1220055 (Why is no real title available?)
• scientific article; zbMATH DE number 2146003 (Why is no real title available?)
• scientific article; zbMATH DE number 194472 (Why is no real title available?)
• scientific article; zbMATH DE number 803211 (Why is no real title available?)
• scientific article; zbMATH DE number 872525 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• Iterative regularization methods for nonlinear ill-posed problems
• Near-optimal column-based matrix reconstruction
• On the Convergence of Stochastic Gradient Descent for Nonlinear Ill-Posed Problems
• On the discrepancy principle for stochastic gradient descent
• On the regularizing property of stochastic gradient descent
• Optimization methods for large-scale machine learning
• Preconditioning Landweber iteration in Hilbert scales
• Probability and random processes.
• Stochastic asymptotical regularization for linear inverse problems
• Stochastic Equations in Infinite Dimensions
• Stochastic gradient descent for linear inverse problems in Hilbert spaces
• Stochastic mirror descent method for linear ill-posed problems in Banach spaces
• Variational methods in imaging

Cited in

(10)

• On a class of linear regression methods
• A posterior contraction for Bayesian inverse problems in Banach spaces
• On the existence of a variational regularization parameter under Morozov's discrepancy principle for nonlinear inverse problems
• ECALL: estimation-calibrated learning for joint deconvolution and kernel inference from unpaired data
• A new strategy for convergence rates of non-stationary asymptotical regularization method for linear inverse problems
• Blow-up of solutions to some classes of ill-posed operator equations and a growth quantification result
• Stochastic asymptotical regularization for nonlinear ill-posed problems
• Revisiting linear machine learning through the perspective of inverse problems
• Continuation problems: theory, numerics, neural networks and applications
• Landweber iteration for inverse problems using multiple repeated measurements data in Banach spaces

This page was built for publication: Stochastic linear regularization methods: random discrepancy principle and applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136777)