Optimal-order convergence of Nesterov acceleration for linear ill-posed problems
From MaRDI portal
Abstract: We show that Nesterov acceleration is an optimal-order iterative regularization method for linear ill-posed problems provided that a parameter is chosen accordingly to the smoothness of the solution. This result is proven both for an a priori stopping rule and for the discrepancy principle. The essential tool to obtain this result is a representation of the residual polynomials via Gegenbauer polynomials.
Recommendations
- On Nesterov acceleration for Landweber iteration of linear ill-posed problems
- Optimal algorithms for linear ill-posed problems yield regularization methods
- On the order optimality of the regularization via inexact Newton iterations
- Accelerated Landweber iterations for the solution of ill-posed equations
- Nonstationary iterated Tikhonov regularization
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A new class of accelerated regularization methods, with application to bioluminescence tomography
- Accelerated Landweber iterations for the solution of ill-posed equations
- Geometry of linear ill-posed problems in variable Hilbert scales
- scientific article; zbMATH DE number 4046975 (Why is no real title available?)
- scientific article; zbMATH DE number 783550 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- Nesterov’s accelerated gradient method for nonlinear ill-posed problems with a locally convex residual functional
- On fractional asymptotical regularization of linear ill-posed problems in Hilbert spaces
- On Nesterov acceleration for Landweber iteration of linear ill-posed problems
- Optimal convergence rates results for linear inverse problems in Hilbert spaces
- Preconditioning Landweber iteration in Hilbert scales
Cited in
(18)- Convergence rates of a dual gradient method for constrained linear ill-posed problems
- On Nesterov acceleration for Landweber iteration of linear ill-posed problems
- On the acceleration of optimal regularization algorithms for linear ill-posed inverse problems
- An analysis of stochastic variance reduced gradient for linear inverse problems *
- On adapting Nesterov's scheme to accelerate iterative methods for linear problems
- A data-driven Kaczmarz iterative regularization method with non-smooth constraints for ill-posed problems
- An iterative method based on Nesterov acceleration for identifying space-dependent source term in a time-fractional diffusion-wave equation
- A Projected Nesterov–Kaczmarz Approach to Stellar Population-Kinematic Distribution Reconstruction in Extragalactic Archaeology
- On inertial iterated Tikhonov methods for solving ill-posed problems
- Anderson acceleration as a Krylov method with application to convergence analysis
- A short-term rational Krylov method for linear inverse problems
- A revisit on Nesterov acceleration for linear ill-posed problems
- A fast algorithm for smooth convex minimization problems and its application to inverse source problems
- Nesterov acceleration-based iterative method for backward problem of distributed-order time-fractional diffusion equation
- Iterative regularization in classification via hinge loss diagonal descent
- An adaptive heavy ball method for ill-posed inverse problems
- Adaptive Nesterov momentum method for solving ill-posed inverse problems
- Regularization of linear inverse problems by rational Krylov methods
This page was built for publication: Optimal-order convergence of Nesterov acceleration for linear ill-posed problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4993898)
