Frame-constrained total variation regularization for white noise regression

DOI10.1214/20-AOS2001MaRDI QIDQ820796zbMATH OpenFDO

Authors Miguel Del Álamo, Housen Li, Axel Munk

Publication date 28 September 2021

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

Full work available at URL https://arxiv.org/abs/1807.02038

zbMATH Keywords

total variationwaveletsnonparametric regressionminimax estimationinterpolation inequalitiesovercomplete dictionaries

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Random fields; image analysis (62M40) Minimax procedures in statistical decision theory (62C20) Numerical methods for wavelets (65T60) White noise theory (60H40)

Abstract: Despite the popularity and practical success of total variation (TV) regularization for function estimation, surprisingly little is known about its theoretical performance in a statistical setting. While TV regularization has been known for quite some time to be minimax optimal for denoising one-dimensional signals, for higher dimensions this remains elusive until today. In this paper we consider frame-constrained TV estimators including many well-known (overcomplete) frames in a white noise regression model, and prove their minimax optimality w.r.t. $L^q$-risk ($1leqq<infty$) up to a logarithmic factor in any dimension $dgeq1$. Overcomplete frames are an established tool in mathematical imaging and signal recovery, and their combination with TV regularization has been shown to give excellent results in practice, which our theory now confirms. Our results rely on a novel connection between frame-constraints and certain Besov norms, and on an interpolation inequality to relate them to the risk functional.

Recommendations

• Optimal convergence rates for Tikhonov regularization in Besov spaces
• Optimal convergence rates for sparsity promoting wavelet-regularization in Besov spaces
• Deconvolution model with fractional Gaussian noise: a minimax study
• Noise estimation in signal restoration using regularization
• Convergence rates for oversmoothing Banach space regularization

Cites work

• scientific article; zbMATH DE number 3143880 (Why is no real title available?)
• scientific article; zbMATH DE number 3907540 (Why is no real title available?)
• scientific article; zbMATH DE number 4080153 (Why is no real title available?)
• scientific article; zbMATH DE number 2001584 (Why is no real title available?)
• scientific article; zbMATH DE number 1522808 (Why is no real title available?)
• A first-order primal-dual algorithm for convex problems with applications to imaging
• A semismooth Newton method for \(\mathrm{L}^1\) data fitting with automatic choice of regularization parameters and noise calibration
• Adaptive estimation over anisotropic functional classes via oracle approach
• Adaptive risk bounds in univariate total variation denoising and trend filtering
• An algorithm for total variation minimization and applications
• An improvement of Rudin-Osher-Fatemi model
• Asymptotic equivalence for nonparametric regression with multivariate and random design
• Asymptotic equivalence of nonparametric regression and white noise
• Automated regularization parameter selection in multi-scale total variation models for image restoration
• Can one use total variation prior for edge-preserving Bayesian inversion?
• Characterizations of Besov-Hardy-Sobolev spaces: A unified approach
• Discrete total variation: new definition and minimization
• Discretization-invariant Bayesian inversion and Besov space priors
• Extensions of smoothing via taut strings
• Extreme value analysis of empirical frame coefficients and implications for denoising by soft-thresholding
• Frame decomposition of decomposition spaces
• Harmonic analysis of the space BV.
• Image Decomposition and Restoration Using Total Variation Minimization and theH¹
• Image decompositions using bounded variation and generalized homogeneous Besov spaces
• Image recovery via total variation minimization and related problems
• Introduction to nonparametric estimation
• Isotonic regression in general dimensions
• Isotonic regression in multi-dimensional spaces and graphs
• Local extremes, runs, strings and multiresolution. (With discussion)
• Locally adaptive regression splines
• Mathematical foundations of infinite-dimensional statistical models
• Measure theory and fine properties of functions
• Minimax estimation via wavelet shrinkage
• Multiresolution parameter choice method for total variation regularized tomography
• Multiscale change point inference. With discussion and authors' reply
• Multiscale change-point segmentation: beyond step functions
• Multiscale scanning in inverse problems
• Multiscale testing of qualitative hypotheses
• Multivariate extensions of isotonic regression and total variation denoising via entire monotonicity and Hardy-Krause variation
• New multiscale transforms, minimum total variation synthesis: Applications to edge-preserving image reconstruction
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• Nonlinear total variation based noise removal algorithms
• Nonparametric estimation of scalar diffusions based on low frequency data
• Nonparametric estimation over shrinking neighborhoods: superefficiency and adaptation
• On Difference-Based Variance Estimation in Nonparametric Regression When the Covariate is High Dimensional
• On a Problem of Adaptive Estimation in Gaussian White Noise
• On adaptive minimax density estimation on R^d
• On improved Sobolev embedding theorems
• On minimax wavelet estimators
• On the prediction performance of the Lasso
• Optimal spatial adaptation to inhomogeneous smoothness: An approach based on kernel estimates with variable bandwidth selectors
• Oscillating patterns in image processing and nonlinear evolution equations. The fifteenth Dean Jacqueline B. Lewis memorial lectures
• Practical Approximate Solutions to Linear Operator Equations When the Data are Noisy
• Shearlet smoothness spaces
• Sparse multidimensional representations using anisotropic dilation and shear operators
• Statistical multiresolution Dantzig estimation in imaging: fundamental concepts and algorithmic framework
• Statistical multiresolution estimation for variational imaging: with an application in Poisson-biophotonics
• Ten Lectures on Wavelets
• Total variation regularization of multi-material topology optimization
• Trend filtering on graphs
• Unconditional bases are optimal bases for data compression and for statistical estimation
• Variance estimation for high-dimensional regression models
• Variational estimators in statistical multiscale analysis
• Variational methods in imaging
• Variational multiscale nonparametric regression: smooth functions

Cited in

(5)

• Multiscale change-point segmentation: beyond step functions
• Multivariate trend filtering for lattice data
• Multiscale total variation estimators for regression and inverse problems
• Convergence rates for oversmoothing Banach space regularization
• Spline smoothing in regression models and asymptotic efficiency in \(L_ 2\)

This page was built for publication: Frame-constrained total variation regularization for white noise regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q820796)