Empirical risk minimization in inverse problems

DOI10.1214/09-AOS726MaRDI QIDQ847644zbMATH OpenFDO

Authors Jussi Klemelä, Enno Mammen

Publication date 19 February 2010

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

Full work available at URL https://arxiv.org/abs/1001.2089

zbMATH Keywords

deconvolutionRadon transformtomographymultivariate density estimationempirical risk minimizationnonparametric function estimation

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Density estimation (62G07) Estimation in multivariate analysis (62H12)

Abstract: We study estimation of a multivariate function $f:mathbf{R}^{d}omathbfR$ when the observations are available from the function $Af$, where $A$ is a known linear operator. Both the Gaussian white noise model and density estimation are studied. We define an $L_2$-empirical risk functional which is used to define a $delta$-net minimizer and a dense empirical risk minimizer. Upper bounds for the mean integrated squared error of the estimators are given. The upper bounds show how the difficulty of the estimation depends on the operator through the norm of the adjoint of the inverse of the operator and on the underlying function class through the entropy of the class. Corresponding lower bounds are also derived. As examples, we consider convolution operators and the Radon transform. In these examples, the estimators achieve the optimal rates of convergence. Furthermore, a new type of oracle inequality is given for inverse problems in additive models.

Recommendations

• On a dense minimizer of empirical risk in inverse problems
• Oracle inequalities for inverse problems
• Asymptotic minimax rates for abstract linear estimators
• Empirical risk minimization as parameter choice rule for general linear regularization methods
• Adaptive estimation for inverse problems with noisy operators

Cites work

• scientific article; zbMATH DE number 5654889 (Why is no real title available?)
• scientific article; zbMATH DE number 3757505 (Why is no real title available?)
• scientific article; zbMATH DE number 47282 (Why is no real title available?)
• scientific article; zbMATH DE number 490141 (Why is no real title available?)
• scientific article; zbMATH DE number 3893753 (Why is no real title available?)
• A central limit theorem under metric entropy with \(L_ 2\) bracketing
• A statistical perspective on ill-posed inverse problems (with discussion)
• Additive regression and other nonparametric models
• Convergence of estimates under dimensionality restrictions
• Empirical risk minimization in inverse problems
• Estimation of Multivariate Regression
• Information-theoretic determination of minimax rates of convergence
• Law of the iterated logarithm for set-indexed partial sum processes with finite variance
• Minimax estimation of the solution of an ill-posed convolution type problem
• Minimax theory of image reconstruction
• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• On density estimation in the view of Kolmogorov's ideas in approximation theory
• On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables
• Optimal rates of convergence for nonparametric statistical inverse problems
• Optimal rates of convergence of estimates in the stochastic problem of computerized tomography
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• Penalized contrast estimator for adaptive density deconvolution
• Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes
• Rates of convergence for minimum contrast estimators
• Renormalization exponents and optimal pointwise rates of convergence
• Speed of estimation in positron emission tomography and related inverse problems
• The cross-validated adaptive epsilon-net estimator
• The existence and asymptotic properties of a backfitting projection algorithm under weak conditions
• Uniform Central Limit Theorems

Cited in

(15)

• Optimal indirect estimation for linear inverse problems with discretely sampled functional data
• Estimation of linear operators from scattered impulse responses
• Adaptive Gaussian inverse regression with partially unknown operator
• Minimax rate of convergence and the performance of empirical risk minimization in phase recovery
• Empirical risk minimization as parameter choice rule for general linear regularization methods
• Oracle inequalities for inverse problems
• Adaptive sup-norm estimation of the Wigner function in noisy quantum homodyne tomography
• The principle of penalized empirical risk in severely ill-posed problems
• Minimax fast rates for discriminant analysis with errors in variables
• Empirical minimization
• Empirical risk minimization in inverse problems
• Noisy discriminant analysis with boundary assumptions
• On a dense minimizer of empirical risk in inverse problems
• Inverse problems with non-compact operators
• Density estimation with minimization of \(U\)-divergence

This page was built for publication: Empirical risk minimization in inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q847644)