Tensor denoising with trend filtering

DOI10.4171/MSL/26MaRDI QIDQ2113264zbMATH OpenFDO

Authors Francesco Ortelli, Sara Van De Geer

Publication date 11 March 2022

Published in Mathematical Statistics and Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.10692

zbMATH Keywords

total variationtrend filteringoracle inequalitiestensor denoisingVitali variation

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: We extend the notion of trend filtering to tensors by considering the $k^{mth}$-order Vitali variation, a discretized version of the integral of the absolute value of the $k^{mth}$-order total derivative. We prove adaptive $el{l}^0$-rates and not-so-slow $el{l}^1$-rates for tensor denoising with trend filtering. For $k=1,2,3,4$ we prove that the $d$-dimensional margin of a $d$-dimensional tensor can be estimated at the $el{l}^0$-rate $n^{-1}$, up to logarithmic terms, if the underlying tensor is a product of $(k-1{)}^{mth}$-order polynomials on a constant number of hyperrectangles. For general $k$ we prove the $el{l}^1$-rate of estimation $n^{-fracH(d)+2k-12H(d)+2k-1}$, up to logarithmic terms, where $H(d)$ is the $d^{mth}$ harmonic number. Thanks to an ANOVA-type of decomposition we can apply these results to the lower dimensional margins of the tensor to prove bounds for denoising the whole tensor. Our tools are interpolating tensors to bound the effective sparsity for $el{l}^0$-rates, mesh grids for $el{l}^1$-rates and, in the background, the projection arguments by Dalalyan et al.

Recommendations

• Adaptive risk bounds in univariate total variation denoising and trend filtering
• Adaptive piecewise polynomial estimation via trend filtering
• Additive models with trend filtering
• Prediction bounds for higher order total variation regularized least squares
• Lower-Rank Tensor Approximation and Multiway Filtering

Cites work

• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 7306926 (Why is no real title available?)
• $\ell_1$ Trend Filtering
• Adaptive estimation of multivariate piecewise polynomials and bounded variation functions by optimal decision trees
• Adaptive piecewise polynomial estimation via trend filtering
• Adaptive risk bounds in univariate total variation denoising and trend filtering
• Additive models with trend filtering
• Analysis versus synthesis in signal priors
• Estimation and testing under sparsity. École d'Été de Probabilités de Saint-Flour XLV -- 2015
• Locally adaptive regression splines
• Multivariate adaptive regression splines
• Multivariate extensions of isotonic regression and total variation denoising via entire monotonicity and Hardy-Krause variation
• New Risk Bounds for 2D Total Variation Denoising
• On the prediction performance of the Lasso
• On the total variation regularized estimator over a class of tree graphs
• On tight bounds for the Lasso
• Oracle inequalities for square root analysis estimators with application to total variation penalties
• Pathwise coordinate optimization
• Prediction bounds for higher order total variation regularized least squares
• Sparsity and Smoothness Via the Fused Lasso
• Trend filtering on graphs

Cited in

(4)

• MARS via lasso
• Variational, Geometric, and Level Set Methods in Computer Vision
• Multivariate trend filtering for lattice data
• The Lasso with structured design and entropy of (absolute) convex hulls

This page was built for publication: Tensor denoising with trend filtering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2113264)