Risk hull method and regularization by projections of ill-posed inverse problems

DOI10.1214/009053606000000542zbMath1246.62082arXivmath/0611228OpenAlexW2034772703MaRDI QIDQ449941

Yuri K. Golubev, Laurent Cavalier

Publication date: 3 September 2012

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0611228

zbMATH Keywords

quadratic riskoracle inequality

Mathematics Subject Classification ID

Related Items (38)

Upper functions for \(\mathbb{L}_{p}\)-norms of Gaussian random fields ⋮ Bayes procedures for adaptive inference in inverse problems for the white noise model ⋮ Early stopping for statistical inverse problems via truncated SVD estimation ⋮ Testing monotonicity of pricing kernels ⋮ Solution of linear ill-posed problems using overcomplete dictionaries ⋮ Solution of linear ill-posed problems by model selection and aggregation ⋮ Adaptivity and Oracle Inequalities in Linear Statistical Inverse Problems: A (Numerical) Survey ⋮ Operator-theoretic and regularization approaches to ill-posed problems ⋮ Optimal Convergence of the Discrepancy Principle for Polynomially and Exponentially Ill-Posed Operators under White Noise ⋮ Upper functions for positive random functionals. I: General setting and Gaussian random functions ⋮ On universal oracle inequalities related to high-dimensional linear models ⋮ Empirical risk minimization as parameter choice rule for general linear regularization methods ⋮ Optimal regularized hypothesis testing in statistical inverse problems ⋮ Theory of adaptive estimation ⋮ Minimax goodness-of-fit testing in ill-posed inverse problems with partially unknown operators ⋮ Semi‐parametric Estimation in a Single‐index Model with Endogenous Variables ⋮ Adaptive complexity regularization for linear inverse problems ⋮ Adaptive spectral regularizations of high dimensional linear models ⋮ A new approach to estimator selection ⋮ Spatially inhomogeneous linear inverse problems with possible singularities ⋮ Sparse model selection under heterogeneous noise: exact penalisation and data-driven thresholding ⋮ Uniform bounds for norms of sums of independent random functions ⋮ Regularization parameter selection in indirect regression by residual based bootstrap ⋮ Multiscale scanning in inverse problems ⋮ Bayesian model selection and the concentration of the posterior of hyperparameters ⋮ Spectral cut-off regularizations for ill-posed linear models ⋮ Comparing parameter choice methods for regularization of ill-posed problems ⋮ The Stein hull ⋮ On oracle inequalities related to data-driven hard thresholding ⋮ Optimal Adaptation for Early Stopping in Statistical Inverse Problems ⋮ Tikhonov-Phillips regularizations in linear models with blurred design ⋮ On the stability of the risk hull method for projection estimators ⋮ Risk hull method for spectral regularization in linear statistical inverse problems ⋮ The empirical process of residuals from an inverse regression ⋮ Beyond the Bakushinkii veto: regularising linear inverse problems without knowing the noise distribution ⋮ Ill-Posed Problems: Operator Methodologies of Resolution and Regularization ⋮ Uncertainty quantification for robust variable selection and multiple testing ⋮ Adaptive estimation over anisotropic functional classes via oracle approach

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A statistical perspective on ill-posed inverse problems (with discussion)
• The principle of penalized empirical risk in severely ill-posed problems
• On the optimal rates of convergence for nonparametric deconvolution problems
• An oracle approach to adaptive estimation of linear functionals in a Gaussian model
• Speed of estimation in positron emission tomography and related inverse problems
• Estimation of the mean of a multivariate normal distribution
• Risk bounds for model selection via penalization
• Oracle inequalities for inverse problems
• Sharp adaptation for inverse problems with random noise
• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• Integral equations. Theory and numerical treatment
• Robust and efficient recovery of a signal passed through a filter and then contaminated by non-Gaussian noise
• Statistical Inverse Estimation in Hilbert Scales
• Block Thresholding and Sharp Adaptive Estimation in Severely Ill-Posed Inverse Problems
• Some Comments on C P
• Gaussian model selection

This page was built for publication: Risk hull method and regularization by projections of ill-posed inverse problems