Empirical risk minimization in inverse problems

DOI10.1214/09-AOS726zbMATH Open1181.62044arXiv1001.2089MaRDI QIDQ847644FDOQ847644

Authors: Jussi Klemelä, Enno Mammen 

Publication date: 19 February 2010

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

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.

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

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

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)

Cites Work

• Title not available (Why is that?)
• Additive regression and other nonparametric models
• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• Title not available (Why is that?)
• The existence and asymptotic properties of a backfitting projection algorithm under weak conditions
• Title not available (Why is that?)
• Convergence of estimates under dimensionality restrictions
• Uniform Central Limit Theorems
• A statistical perspective on ill-posed inverse problems (with discussion)
• Pointwise and sup-norm sharp adaptive estimation of functions on the Sobolev classes
• Minimax theory of image reconstruction
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• A central limit theorem under metric entropy with \(L_ 2\) bracketing
• Rates of convergence for minimum contrast estimators
• On density estimation in the view of Kolmogorov's ideas in approximation theory
• Information-theoretic determination of minimax rates of convergence
• The cross-validated adaptive epsilon-net estimator
• Title not available (Why is that?)
• Speed of estimation in positron emission tomography and related inverse problems
• Penalized contrast estimator for adaptive density deconvolution
• Title not available (Why is that?)
• Optimal rates of convergence for nonparametric statistical inverse problems
• On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables
• Renormalization exponents and optimal pointwise rates of convergence
• Law of the iterated logarithm for set-indexed partial sum processes with finite variance
• Optimal rates of convergence of estimates in the stochastic problem of computerized tomography
• Estimation of Multivariate Regression
• Minimax estimation of the solution of an ill-posed convolution type problem
• Empirical risk minimization in inverse problems

Cited In (15)

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

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)