On Design of Polyhedral Estimates in Linear Inverse Problems

DOI10.1137/22M1543331MaRDI QIDQ6202281zbMATH OpenFDO

Authors Anatoli Juditsky, Arkadi Nemirovski

Publication date 26 March 2024

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2212.12516

zbMATH Keywords

sketchingnonlinear estimationstatistical linear inverse problems

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Linear regression; mixed models (62J05) Estimation in multivariate analysis (62H12)

Abstract: Polyhedral estimate is a generic efficiently computable nonlinear in observations routine for recovering unknown signal belonging to a given convex compact set from noisy observation of signal's linear image. Risk analysis and optimal design of polyhedral estimates may be addressed through efficient bounding of optimal values of optimization problems. Such problems are typically hard; yet, it was shown in Juditsky, Nemirovski 2019 that nearly minimax optimal ("up to logarithmic factors") estimates can be efficiently constructed when the signal set is an ellitope - a member of a wide family of convex and compact sets of special geometry (see, e.g., Juditsky, Nemirovski 2018). The subject of this paper is a new risk analysis for polyhedral estimate in the situation where the signal set is an intersection of an ellitope and an arbitrary polytope allowing for improved polyhedral estimate design in this situation.

Recommendations

• On polyhedral estimation of signals via indirect observations
• Adaptive estimation of convex polytopes and convex sets from noisy data
• Near-optimal recovery of linear and \(N\)-convex functions on unions of convex sets
• Near-optimality of linear recovery from indirect observations

Cites work

• scientific article; zbMATH DE number 3976099 (Why is no real title available?)
• scientific article; zbMATH DE number 4001918 (Why is no real title available?)
• Adaptive Wavelet Galerkin Methods for Linear Inverse Problems
• Adaptive estimation of linear functionals in Hilbert scales from indirect white noise observa\-tions
• Compressive statistical learning with random feature moments
• Computational Methods for Inverse Problems
• Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications
• Discretization effects in statistical inverse problems
• Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
• Multiscale scanning in inverse problems
• Near-optimality of linear recovery from indirect observations
• Near-optimality of linear recovery in Gaussian observation scheme under \(\| \cdot \|_{2}^{2}\)-loss
• Nonlinear estimation for linear inverse problems with error in the operator
• Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition
• Nonparametric estimation by convex programming
• On pointwise adaptive nonparametric deconvolution
• On polyhedral estimation of signals via indirect observations
• Speed of estimation in positron emission tomography and related inverse problems
• Statistical Inference via Convex Optimization
• Statistical Inverse Estimation in Hilbert Scales
• Statistical estimation and optimal recovery
• Variational multiscale nonparametric regression: smooth functions
• Wavelet decomposition approaches to statistical inverse problems

This page was built for publication: On Design of Polyhedral Estimates in Linear Inverse Problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6202281)