Convergence Analysis of Statistical Inverse Problems on Reproducing Kernel Banach Spaces

DOI10.1016/J.JCO.2026.102050MaRDI QIDQ7284855arXivFDO

Authors M. P. Rajan, Darrel K Joseph, M P Rajan

Publication date 17 August 2026

Published in arXiv

Tldr We study the stable approximation of statistical inverse problems on reproducing kernel Banach spaces and establish convergence results using Tikhonov regularization. We provide a rate of convergence in probability for the estimated solution as the number of data points increases, demonstrating the feasibility of our method with numerical experiments.

Full work available at URL https://doi.org/10.1016/J.JCO.2026.102050

Mathematics Subject Classification ID

Linear operators and ill-posed problems, regularization (47A52) Ill-posedness and regularization problems in numerical linear algebra (65F22) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)

arXiv classification

math.FAmath.NAstat.ML

Cites work

• A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
• A parameter choice strategy for the regularized approximation of Fredholm integral equations of the first kind
• Characteristic inequalities of uniformly convex and uniformly smooth Banach spaces
• Convergence analysis of a regularized approximation for solving Fredholm integral equations of the first kind
• Inequalities in Banach spaces with applications
• Regularization methods in Banach spaces.
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes

Cited in

(1)

• Regularization of Statistical Inverse Problems on Non-Reflexive Banach Spaces

This page was built for publication: Convergence Analysis of Statistical Inverse Problems on Reproducing Kernel Banach Spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284855)