2000 character limit reached
Analysis of Generalized Iteratively Regularized Landweber Iterations driven by data (2312.03337v1)
Published 6 Dec 2023 in math.NA and cs.NA
Abstract: We investigate generalized versions of the Iteratively Regularized Landweber Method, initially introduced in [Appl. Math. Optim., 38(1):45-68, 1998], to address linear and nonlinear ill-posed problems. Our approach is inspired by the data-driven perspective emphasized in the introduction by Aspri et al. [Numer. Funct. Anal. Optim., 41(10):1190-1227, 2020]. We provide a rigorous analysis establishing convergence and stability results and present numerical outcomes for linear operators, with the Radon transform serving as a prototype.
- J. Adler and O. Öktem. Solving ill-posed inverse problems using iterative deep neural networks. Inverse Problems, 33(12):124007, 24, 2017.
- Classification of stroke using neural networks in electrical impedance tomography. Inverse Problems, 36(11):115008, 26, 2020.
- Learning the optimal tikhonov regularizer for inverse problems. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 25205–25216. Curran Associates, Inc., 2021.
- Solving inverse problems using data-driven models. Acta Numer., 28:1–174, 2019.
- A data-driven iteratively regularized Landweber iteration. Numer. Funct. Anal. Optim., 41(10):1190–1227, 2020.
- A. B. Bakushinskiĭ. On a convergence problem of the iterative-regularized Gauss-Newton method. Zh. Vychisl. Mat. i Mat. Fiz., 32(9):1503–1509, 1992.
- Neural blind deconvolution with Poisson data. Inverse Problems, 39(5):Paper No. 054003, 30, 2023.
- M. Benning and M. Burger. Modern regularization methods for inverse problems. Acta Numer., 27:1–111, 2018.
- Convex regularization in statistical inverse learning problems. Inverse Probl. Imaging, 17(6):1193–1225, 2023.
- Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography. SIAM J. Imaging Sci., 14(2):470–505, 2021.
- Learning the invisible: a hybrid deep learning–shearlet framework for limited angle computed tomography. Inverse Problems, 35(6):064002, 38, 2019.
- V. Candiani and M. Santacesaria. Neural networks for classification of strokes in electrical impedance tomography on a 3D head model. Math. Eng., 4(4):Paper No. 029, 22, 2022.
- Regularization of inverse problems, volume 375 of Mathematics and its Applications. Kluwer Academic Publishers Group, Dordrecht, 1996.
- M. Haltmeier and L. Nguyen. Regularization of inverse problems by neural networks. In Handbook of mathematical models and algorithms in computer vision and imaging—mathematical imaging and vision, pages 1065–1093. Springer, Cham, [2023] ©2023.
- J. Kaipio and E. Somersalo. Statistical and computational inverse problems, volume 160 of Applied Mathematical Sciences. Springer-Verlag, New York, 2005.
- Iterative regularization methods for nonlinear ill-posed problems, volume 6 of Radon Series on Computational and Applied Mathematics. Walter de Gruyter GmbH & Co. KG, Berlin, 2008.
- B. Kaltenbacher and T.T.N. Nguyen. Discretization of parameter identification in PDEs using neural networks. Inverse Problems, 38(12):Paper No. 124007, 35, 2022.
- Y. Korolev. Two-layer neural networks with values in a Banach space. SIAM J. Math. Anal., 54(6):6358–6389, 2022.
- P. Kuchment. The Radon transform and medical imaging, volume 85 of CBMS-NSF Regional Conference Series in Applied Mathematics. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA, 2014.
- Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
- G. Ólafsson and E .T. Quinto. The Radon Transform, Inverse Problems, and Tomography. Number 63 in Proceeding of Symposia in Applied Mathematics. American Mathematical Society, Providence, Rhode Island, 2006.
- A. Papoulis. The Fourier integral and its applications. McGraw-Hill Book Co. Inc. New York-San Francisco, Calif. London Toronto, 1962.
- O. Scherzer. A modified Landweber iteration for solving parameter estimation problems. Appl. Math. Optim., 38(1):45–68, 1998.
- Gauss-Newton method for solving linear inverse problems with neural network coders. Sampl. Theory Signal Process. Data Anal., 21(2):Paper No. 25, 29, 2023.