Tensor denoising with trend filtering


Loading...

Date

2022

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

We extend the notion of trend filtering to tensors by considering the kth-order Vitali variation – a discretized version of the integral of the absolute value of the kth-order total derivative. We prove adaptive ℓ0-rates and not-so-slow ℓ1-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 ℓ0-rate n−1, up to logarithmic terms, if the underlying tensor is a product of (k−1)th-order polynomials on a constant number of hyperrectangles. For general k we prove the ℓ1-rate of estimation n−H(d)+2k−12H(d)+2k−1, up to logarithmic terms, where H(d) is the dth 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 ℓ0-rates, mesh grids for ℓ1-rates and, in the background, the projection arguments by Dalalyan, Hebiri, and Lederer (2017).

Publication status

published

Editor

Book title

Volume

4

Pages / Article No.

87 - 142

Publisher

European Mathematical Society

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Tenor denoising; total variation; Vitali variation; trend filtering; oracle inequalities

Organisational unit

03717 - van de Geer, Sara (emeritus) / van de Geer, Sara (emeritus) check_circle

Notes

Funding

169011 - Topics in High-Dimensional Statistics (SNF)

Related publications and datasets