Complexity L^0-penalized M-estimation: consistency in more dimensions

DOI10.3390/AXIOMS2030311MaRDI QIDQ402320zbMATH OpenOpenAlexFDO

Authors Laurent Demaret, Felix Friedrich, Gerhard Winkler, Volkmar Liebscher

Publication date 28 August 2014

Published in Axioms (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1301.5492

zbMATH Keywords

adaptive estimationcomplexity penalizedconsistencyconvergence ratesDelaunay triangulationspenalized \(M\)-estimationPotts functionalvariational approachwedgelet partitions

Mathematics Subject Classification ID

Approximation by polynomials (41A10) Rate of convergence, degree of approximation (41A25) Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20)

Abstract: We study the asymptotics in $L^2$ for complexity penalized least squares regression for the discrete approximation of finite-dimensional signals on continuous domains - e.g. images - by piecewise smooth functions. We introduce a fairly general setting which comprises most of the presently popular partitions of signal- or image- domains like interval-, wedgelet- or related partitions, as well as Delaunay triangulations. Then we prove consistency and derive convergence rates. Finally, we illustrate by way of relevant examples that the abstract results are useful for many applications.

Review text

Summary: We study the asymptotics in \(L^2\) for complexity penalized least squares regression for the discrete approximation of finite-dimensional signals on continuous domains -- e.g., images -- by piecewise smooth functions. We introduce a fairly general setting, which comprises most of the presently popular partitions of signal or image domains, like interval, wedgelet or related partitions, as well as Delaunay triangulations. Then, we prove consistency and derive convergence rates. Finally, we illustrate by way of relevant examples that the abstract results are useful for many applications.

Recommendations

• Least squares estimation with complexity penalties
• Aggregation and Sparsity Via ℓ1 Penalized Least Squares
• Consistencies and rates of convergence of jump-penalized least squares estimators
• Scale space consistency of piecewise constant least squares estimators – another look at the regressogram
• Complexity penalized least squares estimators: Analytical results

Cites work

• Complexity penalized least squares estimators: Analytical results
• Consistencies and rates of convergence of jump-penalized least squares estimators
• Don't shed tears over breaks
• Efficient Moment Computation over Polygonal Domains with an Application to Rapid Wedgelet Approximation
• scientific article; zbMATH DE number 724718 (Why is no real title available?)
• scientific article; zbMATH DE number 1433619 (Why is no real title available?)
• Image compression by linear splines over adaptive triangulations
• Minimal penalties for Gaussian model selection
• Minimax theory of image reconstruction
• Modern statistical estimation via oracle inequalities
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• Scale space consistency of piecewise constant least squares estimators – another look at the regressogram
• Smoothers for Discontinuous Signals
• Smoothlets—Multiscale Functions for Adaptive Representation of Images
• Some Convergence Theorems for Independent Random Variables
• Sparse and redundant representations. From theory to applications in signal and image processing.
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Wedgelets: Nearly minimax estimation of edges

Cited in

(6)

• Least squares estimation with complexity penalties
• Approximate \(\ell_0\)-penalized estimation of piecewise-constant signals on graphs
• Scale space consistency of piecewise constant least squares estimators – another look at the regressogram
• Complexity penalized least squares estimators: Analytical results
• Multiscale change point inference. With discussion and authors' reply
• Complexity-penalized estimation of minimum volume sets for dependent data

This page was built for publication: Complexity \(L^0\)-penalized \(M\)-estimation: consistency in more dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q402320)