Smoothed residual stopping for statistical inverse problems via truncated SVD estimation

DOI10.1214/20-EJS1747zbMath1451.65071arXiv1909.13702MaRDI QIDQ2209816

Bernhard Stankewitz

Publication date: 5 November 2020

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.13702

zbMATH Keywords

discrepancy principleadaptive estimationlinear inverse problemsearly stopping criterion

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)

Related Items (3)

Optimal Convergence of the Discrepancy Principle for Polynomially and Exponentially Ill-Posed Operators under White Noise ⋮ Unnamed Item ⋮ Towards adaptivity via a new discrepancy principle for Poisson inverse problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the convergence of the quasioptimality criterion for (iterated) Tikhonov regularization
• Early stopping for statistical inverse problems via truncated SVD estimation
• Adaptive estimation of a quadratic functional by model selection.
• Frequentist coverage of adaptive nonparametric Bayesian credible sets
• On early stopping in gradient descent learning
• Discrepancy principle for statistical inverse problems with application to conjugate gradient iteration
• Boosting With theL₂Loss
• Optimal Adaptation for Early Stopping in Statistical Inverse Problems
• Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities

This page was built for publication: Smoothed residual stopping for statistical inverse problems via truncated SVD estimation