Tensor denoising with trend filtering
Mathematical Statistics and Learning · 2022
DOI: 10.4171/msl/26 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Statistics and Learning, 2022. Verfasst von Francesco Ortelli und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
We extend the notion of trend filtering to tensors by considering the k\mathrm{th} -order Vitali variation – a discretized version of the integral of the absolute value of the k\mathrm{th} -order total derivative. We prove adaptive \ell^0 -rates and not-so-slow \ell^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 \ell^0 -rate n^{-1} , up to logarithmic terms, if the underlying tensor is a product of (k-1)\mathrm{th} -order polynomials on a constant number of hyperrectangles. For general k we prove the \ell^1 -rate of estimation n^{- \frac{H(d)+2k-1}{2H(d)+2k-1}} , up to logarithmic terms, where H(d) is the d\mathrm{th} 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 \ell^0 -rates, mesh grids for \ell^1 -rates and, in the background, the projection arguments by Dalalyan, Hebiri, and Lederer (2017).
Zitieren
APA
Ortelli, F., & Geer, S. V. D. (2022). Tensor denoising with trend filtering. Mathematical Statistics and Learning. https://doi.org/10.4171/msl/26
Vancouver
Ortelli F, Geer SVD. Tensor denoising with trend filtering. Mathematical Statistics and Learning. 2022. doi:10.4171/msl/26
BibTeX
@article{Ortelli2022,
author = {Ortelli, Francesco and Geer, Sara van de},
title = {Tensor denoising with trend filtering},
journal = {Mathematical Statistics and Learning},
year = {2022},
doi = {10.4171/msl/26}
}
EUVIMED