Quadratic functional estimation in inverse problems

DOI10.1016/J.STAMET.2010.05.002zbMATH Open1213.62134arXiv0902.2309OpenAlexW1969343120MaRDI QIDQ537459FDOQ537459

Authors: Cristina Butucea, K. Meziani 

Publication date: 20 May 2011

Published in: Statistical Methodology (Search for Journal in Brave)

Abstract: We consider in this paper a Gaussian sequence model of observations $Y_i$, $igeq1$ having mean (or signal) $het{a}_i$ and variance $sigm{a}_i$ which is growing polynomially like $i^{g}amma$, $gamma>0$. This model describes a large panel of inverse problems. We estimate the quadratic functional of the unknown signal $su{m}_{igeq1}het{a}_i^2$ when the signal belongs to ellipsoids of both finite smoothness functions (polynomial weights $i^{a}lpha$, $alpha>0$) and infinite smoothness (exponential weights $$, $$, $0<rleq2$). We propose a Pinsker type projection estimator in each case and study its quadratic risk. When the signal is sufficiently smoother than the difficulty of the inverse problem ($alpha>gamma+1/4$ or in the case of exponential weights), we obtain the parametric rate and the efficiency constant associated to it. Moreover, we give upper bounds of the second order term in the risk and conjecture that they are asymptotically sharp minimax. When the signal is finitely smooth with $alphaleqgamma+1/4$, we compute non parametric upper bounds of the risk of and we presume also that the constant is asymptotically sharp.

Full work available at URL: https://arxiv.org/abs/0902.2309

Recommendations

• On the estimation of quadratic functionals
• Estimation of quadratic functionals of a density
• Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems
• Estimation of a quadratic functional of a density
• Nonquadratic estimators of a quadratic functional
• Nonparametric estimation of quadratic regression functionals
• Inverse problems for quasi-variational inequalities

zbMATH Keywords

projection estimatorGaussian sequence modelminimax upper boundsparametric ratePinsker estimatorsecond order risk

Mathematics Subject Classification ID

Point estimation (62F10) Markov processes: estimation; hidden Markov models (62M05) Non-Markovian processes: estimation (62M09)

Cites Work

• Oracle inequalities for inverse problems
• Goodness-of-fit testing and quadratic functional estimation from indirect observations
• Adaptive estimation of a quadratic functional of a density by model selection
• Block Thresholding and Sharp Adaptive Estimation in Severely Ill-Posed Inverse Problems
• The principle of penalized empirical risk in severely ill-posed problems
• Nonparametric estimation of the purity of a quantum state in quantum homodyne tomography with noisy data
• On optimal adaptive estimation of a quadratic functional
• Some Problems on Nonparametric Estimation in Gaussian White Noise
• Minimax quadratic estimation of a quadratic functional
• On the estimation of quadratic functionals
• Nonquadratic estimators of a quadratic functional
• Sharp adaptive estimation of quadratic functionals
• Optimal adaptive estimation of a quadratic functional

Cited In (11)

• Sharp minimax tests for large Toeplitz covariance matrices with repeated observations
• Quantitative estimates on Jacobians for hybrid inverse problems
• Adaptive minimax testing for circular convolution
• Estimation of functionals of sparse covariance matrices
• Simple adaptive estimation of quadratic functionals in nonparametric IV models
• Robust estimation in inverse problems via quantile coupling
• Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares
• Gauss Quadratures: An Inverse Problem
• Estimating linear and quadratic forms via indirect observations
• Total variation reconstruction from quadratic measurements
• Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems

This page was built for publication: Quadratic functional estimation in inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q537459)